CN111179943A - Conversation auxiliary equipment and method for acquiring information - Google Patents
Conversation auxiliary equipment and method for acquiring information Download PDFInfo
- Publication number
- CN111179943A CN111179943A CN201911058908.7A CN201911058908A CN111179943A CN 111179943 A CN111179943 A CN 111179943A CN 201911058908 A CN201911058908 A CN 201911058908A CN 111179943 A CN111179943 A CN 111179943A
- Authority
- CN
- China
- Prior art keywords
- features
- voice
- information
- master
- voiceprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000010365 information processing Effects 0.000 claims abstract description 41
- 239000000284 extract Substances 0.000 claims abstract description 7
- 230000008451 emotion Effects 0.000 claims description 94
- 230000033764 rhythmic process Effects 0.000 claims description 9
- 230000002996 emotional effect Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000009432 framing Methods 0.000 description 2
- 210000000214 mouth Anatomy 0.000 description 2
- 210000003928 nasal cavity Anatomy 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 210000001260 vocal cord Anatomy 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 206010013082 Discomfort Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/06—Decision making techniques; Pattern matching strategies
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/22—Interactive procedures; Man-machine interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention discloses conversation auxiliary equipment and a method for acquiring information, and relates to the technical field of electronic equipment. The conversation assistance apparatus includes: the microphone is connected with the information processing module, and the information processing module is connected with the information output module; the information processing module receives a voice signal acquired by a microphone, extracts voice characteristics of the voice signal, and judges whether the voice characteristics are matched with pre-stored voice characteristics corresponding to non-master users according to the voice characteristics, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear conversation auxiliary equipment; if the voice characteristics are matched with the pre-stored voice characteristics corresponding to the non-master user, the personal information of the non-master user corresponding to the voice characteristics is obtained according to the corresponding relation between the pre-stored voice characteristics and the personal information of the non-master user, the personal information of the non-master user is sent to the information output module, and the information output module outputs the personal information of the non-master user. The invention is applicable to person-to-person conversations.
Description
Technical Field
The present invention relates to the field of electronic devices, and in particular, to a conversation assistance device and a method for acquiring information.
Background
With the progress of technology and the development of society, the communication between people is increasingly frequent. In some scenarios, the content involved in the conversation is based on knowing the personal information of the conversation object, for example, in a business meeting, it is necessary to know the personal information such as the job level of the opposite party, which determines whether the content of the conversation with the opposite party is related to specific content or to the overall decision; for another example, in two parties in conversation, party a is not good at observing and analyzing the emotion of the other party, and party b expresses angry emotion, but party a does not timely know the emotion of party b, which easily affects the content of the following conversation, and finally causes the discomforts of both parties a and b, so it is very necessary to timely acquire the personal information of the conversation object, and with the acceleration of the rhythm of life and work, people do not have more time or energy to know the personal information of the object in conversation therewith, or the person participating in conversation is not good at analyzing the personal information of the object in conversation therewith, and finally the conversation effect is poor because the person cannot timely know the personal information of the other party.
Disclosure of Invention
In view of this, embodiments of the present invention provide a conversation assistance device and a method for acquiring information, which are convenient for timely acquiring personal information of an opposite party, so as to solve the problem that the personal information of the opposite party cannot be timely acquired in a conversation process, and finally a conversation effect is deteriorated.
In a first aspect, an embodiment of the present invention provides a conversation assistance apparatus, including: the system comprises a microphone, an information processing module and an information output module, wherein the microphone is connected with the information processing module, and the information processing module is connected with the information output module;
the information processing module receives a voice signal acquired by the microphone, extracts voice features of the voice signal, and judges whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment; if the voice features are matched with the pre-stored voice features corresponding to the non-master users, the personal information of the non-master users corresponding to the voice features is obtained according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users, the personal information of the non-master users is sent to the information output module, and the information output module outputs the personal information of the non-master users.
According to a specific implementation of an embodiment of the present invention, the voice feature includes a voiceprint feature; the information processing module is specifically used for receiving the voice signals collected by the microphone, extracting voiceprint features of the voice signals, and judging whether the voiceprint features are matched with prestored voiceprint features corresponding to non-master users or not according to the voiceprint features.
According to a specific implementation manner of the embodiment of the present invention, the voice characteristics further include vocabulary characteristics and/or prosodic characteristics, and the personal information is emotion information; the information processing module is further used for obtaining emotion information of the non-main user corresponding to the vocabulary features and/or the rhythm features according to the corresponding relation between the prestored vocabulary features and/or the rhythm features and the emotion information of the non-main user if the voiceprint features are matched with the prestored voiceprint features corresponding to the non-main user, sending the emotion information of the non-main user to the information output module, and outputting the emotion information of the non-main user by the information output module.
According to a specific implementation manner of the embodiment of the present invention, the information processing module is further configured to determine whether the voiceprint feature matches a voiceprint feature corresponding to a pre-stored non-master user; and if the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users, establishing and storing the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features.
According to a specific implementation manner of the embodiment of the present invention, the information processing module further includes: the voice prompt system comprises a prompt information submodule and a command receiving submodule, wherein the prompt information submodule is used for sending prompt information for judging whether the voice signal is stored or not if the voiceprint characteristics are not matched with the prestored voiceprint characteristics corresponding to the non-master user; the command receiving sub-module is used for receiving a storage command of the main user and storing the voice signal. .
According to a specific implementation manner of the embodiment of the invention, the information output module is a brain-computer interface module.
According to a specific implementation manner of the embodiment of the invention, the conversation auxiliary device is an earphone or a mobile phone.
In a second aspect, an embodiment of the present invention provides an information obtaining method, including: receiving a voice signal; extracting voice characteristics corresponding to the voice signals; judging whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment; if the voice features are matched with pre-stored voice features corresponding to non-master users, obtaining personal information of the non-master users corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users; sending the personal information of the non-master user to an information output module, wherein the information output module outputs the personal information of the non-master user; alternatively, the first and second electrodes may be,
if the voice characteristics are the voice characteristics corresponding to the non-master users, the voice characteristics are sent to a cloud end, so that the cloud end obtains the personal information of the non-master users corresponding to the voice characteristics according to the corresponding relation between the pre-stored voice characteristics and the personal information of the non-master users; and receiving the personal information of the non-master user sent by the cloud to the information output module so that the information output module outputs the personal information of the non-master user.
According to a specific implementation of an embodiment of the present invention, the voice feature includes a voiceprint feature; and judging whether the voice features are matched with pre-stored voice features corresponding to non-master users or not according to the voice features, specifically judging whether the voiceprint features are matched with pre-stored voiceprint features corresponding to non-master users or not according to the voiceprint features.
According to a specific implementation manner of the embodiment of the present invention, the voice characteristics further include vocabulary characteristics and/or prosodic characteristics, and the personal information is emotion information; if the voice features are matched with the pre-stored voice features corresponding to the non-master user, obtaining the personal information of the non-master user corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master user, and specifically, if the voiceprint features are matched with the pre-stored voiceprint features corresponding to the non-master user, obtaining the emotion information of the non-master user corresponding to the vocabulary features and/or the prosodic features according to the corresponding relation between the pre-stored vocabulary features and/or the prosodic features and the emotion information of the non-master user.
According to a specific implementation manner of the embodiment of the present invention, the method further includes: judging whether the voiceprint features are matched with the prestored voiceprint features corresponding to the non-master users; and if the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users, establishing and storing the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features.
According to a specific implementation manner of the embodiment of the present invention, after the voiceprint feature is not matched with a voiceprint feature corresponding to a pre-stored non-master user, before the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature is established and stored, the method further includes: sending prompt information whether to store the voice signal; receiving a storage command of the master user; and storing the voice signal according to the storage command.
According to a specific implementation manner of the embodiment of the present invention, the personal information includes: identity information, background information, and/or mood information.
According to a specific implementation manner of the embodiment of the invention, the information output module is a brain-computer interface module.
According to the conversation auxiliary equipment and the method for acquiring information, the microphone is connected with the information processing module, and the information processing module is connected with the information output module; the information processing module receives a voice signal acquired by the microphone, extracts voice features of the voice signal, and judges whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment; if the voice characteristics corresponding to the pre-stored non-master user are matched, the personal information of the non-master user corresponding to the voice characteristics is obtained according to the corresponding relation between the pre-stored voice characteristics and the personal information of the non-master user, the personal information is sent to the information output module, and the personal information is output by the information output module.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a first embodiment of a conversation assistance apparatus provided in the present invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a second embodiment of a conversation assistance apparatus provided in the present invention;
fig. 4 is a schematic flowchart of a third embodiment of a method for acquiring information according to the present invention;
fig. 5 is a flowchart illustrating a fourth embodiment of a method for acquiring information according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic structural diagram of a first embodiment of a conversation assistance device provided by the present invention, as shown in fig. 1, the conversation assistance device of the present embodiment is applied in a face-to-face conversation or a call communication process, and includes: the system comprises a microphone 11, an information processing module 12 and an information output module 13, wherein the microphone 11 is connected with the information processing module 12, and the information processing module 12 is connected with the information output module 13;
the information processing module 13 receives the voice signal acquired by the microphone 11, extracts the voice feature of the voice signal, and judges whether the voice feature is matched with the voice feature corresponding to a pre-stored non-master user according to the voice feature, wherein the non-master user is a user who has a conversation with a master user, and the master user is a user who wears the conversation auxiliary device; if the voice feature is matched with a pre-stored voice feature corresponding to a non-master user, the personal information of the non-master user corresponding to the voice feature is obtained according to the corresponding relation between the pre-stored voice feature and the personal information of the non-master user, the personal information is sent to the information output module 13, and the information output module 13 plays the personal information.
In this embodiment, the number of the pre-stored non-master users may be one or multiple; the source of the voice signal is a sound signal emitted by a person; the speech features may include prosodic features, psychoacoustic features, spectral features, lexical features, and voiceprint features; because the voiceprint characteristics of each person are different, the voice signals converted from the voices spoken by different persons are different, and the corresponding voice characteristics are also different, different persons can be distinguished according to the voice characteristics; the process of extracting the voice features of the voice signal can comprise the steps of carrying out pre-emphasis processing on the voice signal, carrying out framing and windowing operation on the processed voice data, then carrying out fast Fourier transform and logarithm operation processing, and finally carrying out discrete cosine transform to obtain the voice features.
The master user is a user wearing the conversation auxiliary equipment in the conversation, and the non-master user is a user in the conversation with the master user; in an actual application scene, the number of people participating in the conversation can be two or more than two, the users participating in the conversation can wear the conversation auxiliary equipment, the user wearing the conversation auxiliary equipment is a master user, and the user carrying out conversation relative to the master user is a non-master user.
The corresponding relation between the voice features and the personal information of the non-master user can be prestored in the local area or the cloud end, and as an optional implementation mode, the corresponding relation between the voice features and the personal information of the non-master user is prestored in the cloud end.
In this embodiment, the information processing module sends the voice feature to a cloud end, in the cloud end, the personal information of the non-master user corresponding to the voice feature is obtained according to a correspondence between the pre-stored voice feature and the personal information of the non-master user, the cloud end sends the personal information of the non-master user to the information output module, and the information output module outputs the personal information of the non-master user.
According to the embodiment, the personal information of the non-master user corresponding to the voice feature is obtained at the cloud according to the corresponding relation of the pre-stored voice feature and the non-master user personal information, so that a plurality of users using the dialogue auxiliary system can share the corresponding relation of the voice feature and the non-master user personal information conveniently, the situation that the corresponding relation of the voice feature and the non-master user personal information needs to be reestablished due to damage or loss of the dialogue auxiliary system is avoided, and convenience in using the dialogue auxiliary system by the users is improved.
As an optional embodiment, the personal information may be identity information, background information and/or emotion information, and the identity information may specifically be name, year and month of birth, unit of residence, job, and the like; the background information may be family status, address, hobbies, specialties, etc.; the emotional information may be happy, angry, sad, excited, etc. information.
As an optional embodiment, the information output module may be a voice broadcast module or a brain-computer interface module.
In this embodiment, the microphone is connected to the information processing module, and the information processing module is connected to the information output module; the information processing module receives the voice signal acquired by the microphone, extracts the voice feature of the voice signal, judges whether the voice feature is matched with the voice feature corresponding to a pre-stored non-master user or not according to the voice feature, if the voice feature is matched with the voice feature corresponding to the pre-stored non-master user, obtains the personal information of the non-master user corresponding to the voice feature according to the corresponding relation of the pre-stored voice feature and the personal information of the non-master user, and sends the personal information to the information output module, and the information output module outputs the personal information. And the conversation process is more smooth, and the conversation efficiency is improved.
As an alternative embodiment, the speech features include voiceprint features; the information processing module is specifically used for receiving the voice signals collected by the microphone, extracting voiceprint features of the voice signals, and judging whether the voiceprint features are matched with prestored voiceprint features corresponding to non-master users or not according to the voiceprint features.
In this embodiment, the voiceprint feature is a feature related to a speaker, the voiceprint is a sound wave spectrum carrying speech information displayed by an electro-acoustic instrument, the voiceprint is related to an organ generated by a human body, and the vocal organs include vocal cords, a soft jaw, a tongue, teeth, lips, and the like; the sounding resonance device comprises a pharyngeal cavity, an oral cavity and a nasal cavity. The voiceprint features are used to reflect a set of feature vectors for the voiceprint, including formants, spectral energy distribution, harmonic-to-noise ratio, and the like.
In this embodiment, it is determined whether the voiceprint feature matches a voiceprint feature corresponding to a pre-stored non-master user, which specifically may be: pre-establishing a voiceprint model base, wherein non-master users and corresponding voiceprint models are stored in the voiceprint model base, each non-master user corresponds to one voiceprint model, and each voiceprint model corresponds to the voiceprint characteristics of the non-master users; the extracted voiceprint features are used as input of a voiceprint model, probability values corresponding to the voiceprint features are calculated in a traversing mode, when the voiceprint features corresponding to the voiceprint model with the probability values exceeding a certain set threshold value exist, namely the voiceprint features are matched with the voiceprint features corresponding to the pre-stored non-master users, furthermore, the voiceprint features corresponding to the voiceprint model with the maximum probability values exist in a plurality of probability values exceeding the certain set threshold value, namely the voiceprint features are matched with the voiceprint features corresponding to the pre-stored non-master users; and when all the probability values do not exceed a certain set threshold value, the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users.
Furthermore, each non-master user corresponds to one voiceprint model, so that the non-master user can be correspondingly determined according to the voiceprint model with the maximum probability value, and then the identity information and/or the background information corresponding to the non-master user can be determined according to the relationship between the non-master user and the corresponding identity information and/or the background information.
This embodiment, through the voiceprint feature that draws corresponding to the speech signal that receives, again according to the voiceprint feature, judge whether the voiceprint feature matches with the voiceprint feature that the non-master user that prestores corresponds to the judged result is for the matching back, acquires the personal information of non-master user again, like this, can improve the efficiency that the master user acquireed non-master user information, improves the use experience of master user simultaneously.
As an alternative embodiment, on the basis of the above embodiment, the voice feature further includes a prosodic feature, and the personal information is emotion information; the information processing module is further used for obtaining emotion information of the non-master user corresponding to the rhythm characteristics according to the corresponding relation between the prestored rhythm characteristics and emotion information of the non-master user if the voiceprint characteristics are matched with the prestored voiceprint characteristics corresponding to the non-master user, sending the emotion information of the non-master user to the information output module, and outputting the emotion information of the non-master user by the information output module.
In the embodiment, the corresponding relation between the prosodic features and the emotion information of the non-master user can be established through the emotion database; pre-storing a plurality of emotion sub-libraries in an emotion database, wherein each emotion sub-library stores rhythm characteristics corresponding to the emotion; and taking prosodic features extracted from the voice signals as input of an emotion database, and carrying out similarity calculation on the prosodic features and the prosodic features in each pre-stored emotion sub-database, wherein the emotion corresponding to the emotion sub-database with the highest score is the emotion of a non-master user in the current conversation.
As an alternative embodiment, on the basis of the above embodiment, the voice feature further includes a vocabulary feature, and the personal information is emotion information; the information processing module is further used for obtaining emotion information of the non-master user corresponding to the vocabulary features according to the corresponding relation between the prestored vocabulary features and the emotion information of the non-master user if the voiceprint features are matched with the voiceprint features corresponding to the prestored non-master user, sending the emotion information of the non-master user to the information output module, and outputting the emotion information of the non-master user by the information output module.
In the embodiment, the corresponding relation between the vocabulary characteristics and the emotion information of the non-master user can be specifically established through the emotion database; pre-storing a plurality of emotion sub-libraries in an emotion database, wherein each emotion sub-library stores vocabulary characteristics corresponding to the emotion; and taking the vocabulary characteristics extracted from the voice signals as input of an emotion database, scoring the input vocabulary characteristics by each emotion sub-database, and taking the emotion corresponding to the emotion sub-database with the highest score as the emotion of a non-master user in the current conversation.
It can be understood that the final emotion information can be obtained by comprehensively judging the results obtained by the lexical characteristics and the prosodic characteristics, and the specific process is the prior art and is not described herein again.
As an optional embodiment, the information processing module is further configured to determine whether the voiceprint feature matches a voiceprint feature that is pre-stored and corresponds to a non-master user; and if the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users, establishing and storing the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features.
In this embodiment, if the voiceprint feature is not matched with a pre-stored voiceprint feature corresponding to a non-master user, a corresponding relationship between the voiceprint feature and personal information corresponding to the voiceprint feature is established and stored, so that subsequent acquisition of more personal information of the non-master user is facilitated.
As an optional embodiment, the information processing module further includes: the prompt information sub-module is used for sending prompt information for storing the voice signal or not if the voiceprint features are not matched with the voiceprint features corresponding to the pre-stored non-master users; the command receiving sub-module is used for receiving a storage command of the main user and storing the voice signal.
In this embodiment, the prompt message may be a voice broadcast or a text prompt; the speech signal may include all information that the user speaks to include, such as vocabulary, timbre, pitch, frequency, voiceprint, and the like; the voice signal can provide linguistic data for the establishment of the voiceprint model and the emotion database, and the voiceprint model corresponding to the non-master user and the emotion database can be conveniently established.
It can be understood that, in the above embodiment, after the voice signal is stored, the voiceprint feature corresponding to the voice signal can be extracted, and the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature is established and stored; and the vocabulary characteristics and/or prosodic characteristics corresponding to the voice signals can be extracted, and the corresponding relation between the vocabulary characteristics and/or prosodic characteristics and emotion information of a non-main user is established and stored.
As an optional embodiment, the user may select not to store the voiceprint feature that does not match the voiceprint feature corresponding to the pre-stored non-master user, and the specific implementation manner may be that the voiceprint feature is not stored by selecting a button of the word "not store", or that the sent prompt information whether to store the voiceprint feature is stored, and within a predetermined time, when the user does not perform an operation, the voiceprint feature automatically disappears, that is, the voiceprint feature is not stored.
In this embodiment, by sending the prompt information indicating whether to store the voiceprint feature to the user, when the user determines to store the voiceprint feature, the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature is established and stored, so that the user can use the dialog assistance device flexibly.
As an optional embodiment, the system further includes a sending module, configured to send the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature to a server.
In this embodiment, the corresponding relationship between the voiceprint features and the personal information corresponding to the voiceprint features is sent to the server, so that a plurality of users using the dialogue assistance system can share the corresponding relationship between the voice features and the personal information of the non-master user, the situation that the corresponding relationship between the voice features and the personal information of the non-master user needs to be reestablished due to damage or loss of the dialogue assistance system is avoided, and the convenience of the users using the dialogue assistance system is improved.
As an alternative embodiment, the conversation aid is a headset or a mobile phone.
In this embodiment, when the conversation auxiliary device is an earphone, the information output module may be an electroacoustic conversion module provided in the earphone; when the conversation auxiliary equipment is a mobile phone, the information output module can be an interface which is arranged on the mobile phone and connected with a common earphone through the interface, and a master user can acquire personal information of a non-master user, or the mobile phone has a wireless communication function and can be in communication connection with the wireless earphone, and the master user can also acquire the personal information of the non-master user.
The following describes a specific application of an embodiment of the present invention with reference to fig. 2. Fig. 2 is a schematic diagram of an embodiment of the present invention. In this embodiment, the conversation auxiliary device is the earphone 1, and the earphone 1 is connected with the intelligent terminal 2 through bluetooth.
In this embodiment, the intelligent terminal 2 may be a mobile phone or a watch; in the process of face-to-face conversation, the earphone 1 receives a voice signal acquired by a microphone 11 through an information processing module 12, extracts voiceprint features in the voice signal, judges that the voiceprint features are matched with prestored voiceprint features corresponding to non-master users according to the voiceprint features, obtains background information of the non-master users according to the corresponding relation between the voiceprint features and the background information of the non-master users, and broadcasts the background information to the master users through the earphone;
if the voiceprint features corresponding to the pre-stored non-master user are not matched, a prompt command is sent to the intelligent terminal 2 through the Bluetooth, whether prompt information of the voiceprint features is stored or not is displayed on the intelligent terminal, the master user confirms and stores the prompt information on the intelligent terminal, then the voiceprint features and corresponding personal information are stored, and after the storage, the stored content can be sent to the cloud server 3. And when the user does not operate the prompt message within the preset time, the prompt message disappears, namely the voiceprint feature and the corresponding personal information are not stored.
It is understood that the personal information may be input through the smart terminal.
Fig. 3 is a schematic structural diagram of a second embodiment of a dialog assisting device provided by the present invention, as shown in fig. 3, including: a microphone 11, an information processing module 12 and a brain-computer interface module 131; the microphone 11 is connected with the information processing module 12, and the information processing module 12 is connected with the brain-computer interface module 131
In this embodiment, the processing result of the information processing module 12 is directly input to the brain of the primary user through the brain-computer interface module 131, so that the user can more quickly obtain personal information of non-primary users.
Fig. 4 is a flowchart illustrating a third embodiment of a method for acquiring information according to the present invention, as shown in fig. 4, in a process of applying a face-to-face conversation or a call communication, the method of this embodiment may include:
In this embodiment, the received voice signals may be voice signals sent by all users in the conversation process.
And 102, extracting the voice characteristics corresponding to the voice signals.
In this embodiment, a voice feature corresponding to a received voice signal is extracted from the received voice signal; the speech features may include prosodic features, psychoacoustic features, spectral features, lexical features, and voiceprint features; because the voiceprint characteristics of each person are different, the voice signals converted from the voices spoken by different persons are different, and the corresponding voice characteristics are also different, different persons can be distinguished according to the voice characteristics; the process of extracting the voice features of the voice signal can comprise the steps of carrying out pre-emphasis processing on the voice signal, carrying out framing and windowing operation on the processed voice data, then carrying out fast Fourier transform and logarithm operation processing, and finally carrying out discrete cosine transform to obtain the voice features.
And 103, judging whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment.
In this embodiment, the number of the pre-stored non-master users may be one or multiple; the master user is a user wearing the conversation auxiliary equipment in the conversation, and the non-master user is a user in the conversation with the master user; in an actual application scene, the number of people participating in the conversation can be two or more than two, the users participating in the conversation can wear the conversation auxiliary equipment, the user wearing the conversation auxiliary equipment is a master user, and the user carrying out conversation relative to the master user is a non-master user.
The master user hopes to connect with the personal information of the non-master user by the aid of the dialogue auxiliary equipment, and whether the received voice signal is sent by the master user or the non-master user can be distinguished according to the pre-stored voice characteristics corresponding to the non-master user.
And step 104, if the voice features are matched with the pre-stored voice features corresponding to the non-master users, obtaining the personal information of the non-master users corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users.
In this embodiment, the correspondence between the voice feature and the personal information of the non-master user may be pre-stored locally or in the cloud.
In an embodiment of the present invention, the personal information may be identity information, background information and/or emotion information, and the identity information may specifically be name, year and month of birth, unit of the birth, job, and the like; the background information may be family status, address, hobbies, specialties, etc.; the emotional information may be happy, angry, sad, excited, etc. information.
And 105, sending the personal information of the non-master user to an information output module so that the information output module outputs the personal information of the non-master user.
In this embodiment, the output mode may be voice output or text output.
In an embodiment of the present invention, the output module may be a voice output module or a brain-computer interface module.
In this embodiment, by extracting a voice feature corresponding to the voice signal, according to the voice feature, it is determined whether the voice feature is a pre-stored voice feature corresponding to a non-master user, where the non-master user is a user performing a dialogue with a master user, and the master user is a user wearing the dialogue assistance device; if the voice feature is the voice feature corresponding to the non-master user, obtaining the personal information of the non-master user corresponding to the voice feature according to the corresponding relation between the voice feature pre-stored locally and the personal information of the non-master user; the personal information of the non-master user is sent to the information output module, and the information output module outputs the personal information of the non-master user, so that the master user can conveniently and timely acquire the personal information of the non-master user in the conversation process, the condition of the non-master user can be known, and the conversation effect is improved. And the conversation process is more smooth, and the conversation efficiency is improved.
Fig. 5 is a flowchart illustrating a fourth embodiment of a method for acquiring information according to the present invention, as shown in fig. 5, in a face-to-face conversation, the method of the present embodiment may include:
In this embodiment, the received voice signals may be voice signals sent by all users in the conversation process.
In this embodiment, the method is similar to the method for extracting the speech feature described in step 102, and is not described here again.
And 203, judging whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment.
In this embodiment, the method is similar to the method for extracting the speech feature described in step 103, and is not described here again.
And 204, if the voice features are matched with the pre-stored voice features corresponding to the non-master users, sending the voice features to a cloud end, so that the cloud end obtains the personal information of the non-master users corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users.
In the embodiment, the personal information of the non-master user can be obtained according to the voice characteristics corresponding to the non-master user; the personal information can be identity information, background information and/or emotion information, and the identity information can be specifically name, birth year and month, unit of birth and job; the background information may be family status, address, hobbies, specialties, etc.; the background information may be; the emotional information may be happy, angry, sad, excited, etc. information.
In the embodiment, the cloud end sends the obtained personal information of the non-master user to the information output module, and the output module outputs the personal information of the non-master user; the output mode may specifically be speech output.
In an embodiment of the present invention, the output module may be a voice output module or a brain-computer interface module.
According to the embodiment, the personal information of the non-master user corresponding to the voice feature is obtained through the cloud according to the corresponding relation of the pre-stored voice feature and the non-master user personal information, so that a plurality of users using the dialogue auxiliary system can share the corresponding relation of the voice feature and the non-master user personal information conveniently, the situation that the corresponding relation of the voice feature and the non-master user personal information needs to be re-established due to damage or loss of the dialogue auxiliary system is avoided, and convenience of the user using the dialogue auxiliary system is improved.
In an embodiment of the present invention, the voice feature includes a voiceprint feature; and judging whether the voice features are matched with pre-stored voice features corresponding to non-master users or not according to the voice features, specifically judging whether the voiceprint features are matched with pre-stored voiceprint features corresponding to non-master users or not according to the voiceprint features.
In this embodiment, the voiceprint feature is a feature related to a speaker, the voiceprint is a sound wave spectrum carrying speech information displayed by an electro-acoustic instrument, the voiceprint is related to an organ generated by a human body, and the vocal organs include vocal cords, a soft jaw, a tongue, teeth, lips, and the like; the sounding resonance device comprises a pharyngeal cavity, an oral cavity and a nasal cavity. The voiceprint features are used to reflect a set of feature vectors for the voiceprint, including formants, spectral energy distribution, harmonic-to-noise ratio, and the like.
In this embodiment, it is determined whether the voiceprint feature matches a voiceprint feature corresponding to a pre-stored non-master user, which specifically may be: pre-establishing a voiceprint model base, wherein non-master users and corresponding voiceprint models are stored in the voiceprint model base, each non-master user corresponds to one voiceprint model, and each voiceprint model corresponds to the voiceprint characteristics of the non-master users; the extracted voiceprint features are used as input of a voiceprint model, probability values corresponding to the voiceprint features are calculated in a traversing mode, when the voiceprint features corresponding to the voiceprint model with the probability values exceeding a certain set threshold value exist, namely the voiceprint features are matched with the voiceprint features corresponding to the pre-stored non-master users, furthermore, the voiceprint features corresponding to the voiceprint model with the maximum probability values exist in a plurality of probability values exceeding the certain set threshold value, namely the voiceprint features are matched with the voiceprint features corresponding to the pre-stored non-master users; and when all the probability values do not exceed a certain set threshold value, the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users.
This embodiment, through according to the voiceprint feature, judge whether the speech feature matches with the voiceprint feature that the non-master user that prestores corresponds to the judged result is for the back of matching, acquires the personal information of non-master user again, like this, can improve the efficiency that the master user acquireed non-master user information, improves the use experience of master user simultaneously.
In an embodiment of the present invention, on the basis of the above embodiment, the voice feature further includes a prosodic feature, and the personal information is emotion information; if the voice feature is matched with the pre-stored voice feature corresponding to the non-master user, obtaining the personal information of the non-master user corresponding to the voice feature according to the corresponding relation between the pre-stored voice feature and the personal information of the non-master user, and specifically, if the voiceprint feature is matched with the pre-stored voiceprint feature corresponding to the non-master user, obtaining the emotional information of the non-master user corresponding to the prosodic feature according to the corresponding relation between the pre-stored prosodic feature and the emotional information of the non-master user.
In the embodiment, the corresponding relation between the prosodic features and the emotion information of the non-master user can be established through the emotion database; pre-storing a plurality of emotion sub-libraries in an emotion database, wherein each emotion sub-library stores rhythm characteristics corresponding to the emotion; and taking prosodic features extracted from the voice signals as input of an emotion database, and carrying out similarity calculation on the prosodic features and the prosodic features in each pre-stored emotion sub-database, wherein the emotion corresponding to the emotion sub-database with the highest score is the emotion of a non-master user in the current conversation.
It can be understood that after the emotion information of the non-primary user is obtained according to the prosodic features, the emotion information of the non-primary user can be sent to the information output module, so that the information output module outputs the emotion information of the non-primary user.
As an alternative embodiment, on the basis of the above embodiment, the voice feature further includes a vocabulary feature, and the personal information is emotion information; and the information processing module is also used for obtaining the emotion information of the non-master user corresponding to the vocabulary characteristics according to the corresponding relation between the prestored vocabulary characteristics and the emotion information of the non-master user if the voiceprint characteristics are matched with the prestored voiceprint characteristics corresponding to the non-master user.
In the embodiment, the corresponding relation between the vocabulary characteristics and the emotion information of the non-master user can be specifically established through the emotion database; pre-storing a plurality of emotion sub-libraries in an emotion database, wherein each emotion sub-library stores vocabulary characteristics corresponding to the emotion; and taking the vocabulary characteristics extracted from the voice signals as input of an emotion database, scoring the input vocabulary characteristics by each emotion sub-database, and taking the emotion corresponding to the emotion sub-database with the highest score as the emotion of a non-master user in the current conversation.
It can be understood that after the emotion information of the non-primary user is obtained according to the vocabulary features, the emotion information of the non-primary user can be sent to the information output module, so that the information output module outputs the emotion information of the non-primary user.
It can be understood that the final emotion information can be obtained by comprehensively judging the results obtained by the lexical characteristics and the prosodic characteristics, and the specific process is the prior art and is not described herein again.
In an embodiment of the present invention, the method further includes:
judging whether the voiceprint features are matched with the prestored voiceprint features corresponding to the non-master users; and if the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users, establishing and storing the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features.
In this embodiment, when the voiceprint feature is not a voiceprint feature corresponding to a non-master user, a correspondence between the voiceprint feature and personal information corresponding to the voiceprint feature is established and stored.
In this embodiment, by judging that the voiceprint feature is not a pre-stored voiceprint feature corresponding to a non-master user, a corresponding relationship between the voiceprint feature and personal information corresponding to the voiceprint feature is established and stored, so that subsequent acquisition of more personal information of the non-master user is facilitated.
In an embodiment of the present invention, after the voiceprint feature is not matched with a pre-stored voiceprint feature corresponding to a non-master user, before establishing and storing a corresponding relationship between the voiceprint feature and personal information corresponding to the voiceprint feature, the method further includes:
sending prompt information whether to store the voice signal;
in this embodiment, the prompt message may be a voice broadcast or a text prompt; the speech signal may include all information that the user speaks to include, such as vocabulary, timbre, pitch, frequency, voiceprint, and the like; the speech signal may provide the corpus for the creation of the voiceprint model and the emotion database.
And receiving a storage command of the master user.
In this embodiment, a command for determining storage by the master user is received.
And storing the voice signal according to the storage command.
In this embodiment, after receiving a storage command of a master user, a corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature is established and stored according to the storage command.
In this embodiment, prompt information indicating whether to store the voiceprint feature is sent to the user, and when the user determines to store the voiceprint feature, the voice signal is stored, so that the user can flexibly select whether to store the voice signal, the corpus can be provided for establishing a voiceprint model and an emotion database, and the voiceprint model corresponding to a non-master user and the emotion database can be conveniently established.
It can be understood that, in the above embodiment, after the voice signal is stored, the voiceprint feature corresponding to the voice signal can be extracted, and the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature is established and stored; and the vocabulary characteristics and/or prosodic characteristics corresponding to the voice signals can be extracted, and the corresponding relation between the vocabulary characteristics and/or prosodic characteristics and emotion information of a non-main user is established and stored.
In an embodiment of the present invention, a user may select not to store a voiceprint feature that does not match a voiceprint feature corresponding to a pre-stored non-master user, and a specific implementation manner may be that the voiceprint feature is not stored by selecting a button of a "do not store" character, or that prompt information is sent whether to store the voiceprint feature, and the voiceprint feature automatically disappears when the user does not perform an operation within a predetermined time, that is, the voiceprint feature is not stored.
In an embodiment of the present invention, after the establishing and storing the corresponding relationship between the voiceprint feature and the personal information corresponding to the voiceprint feature, the method further includes: and sending the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features to a server.
In this embodiment, the corresponding relationship between the voiceprint features and the personal information corresponding to the voiceprint features is sent to the server, so that a plurality of users using the dialogue assistance system can share the corresponding relationship between the voice features and the personal information of the non-master user, the situation that the corresponding relationship between the voice features and the personal information of the non-master user needs to be reestablished due to damage or loss of the dialogue assistance system is avoided, and the convenience of the users using the dialogue assistance system is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The term "comprising", without further limitation, means that the element so defined is not excluded from the group consisting of additional identical elements in the process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A conversation assistance apparatus, comprising: the system comprises a microphone, an information processing module and an information output module, wherein the microphone is connected with the information processing module, and the information processing module is connected with the information output module; the information processing module receives a voice signal acquired by the microphone, extracts voice features of the voice signal, and judges whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment; if the voice features are matched with the pre-stored voice features corresponding to the non-master users, the personal information of the non-master users corresponding to the voice features is obtained according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users, the personal information of the non-master users is sent to the information output module, and the information output module outputs the personal information of the non-master users.
2. The conversation assistance apparatus according to claim 1, wherein the speech feature comprises a voiceprint feature; the information processing module is specifically used for receiving the voice signals collected by the microphone, extracting voiceprint features of the voice signals, and judging whether the voiceprint features are matched with prestored voiceprint features corresponding to non-master users or not according to the voiceprint features.
3. The conversation assistance device of claim 2, wherein the speech features further comprise lexical features and/or prosodic features, and the personal information is emotional information; the information processing module is further used for obtaining emotion information of the non-main user corresponding to the vocabulary features and/or the rhythm features according to the corresponding relation between the prestored vocabulary features and/or the rhythm features and the emotion information of the non-main user if the voiceprint features are matched with the prestored voiceprint features corresponding to the non-main user, sending the emotion information of the non-main user to the information output module, and outputting the emotion information of the non-main user by the information output module.
4. The dialogue assistance device according to claim 2, wherein the information processing module is further configured to determine whether the voiceprint feature matches a voiceprint feature corresponding to a pre-stored non-primary user; and if the voiceprint features are not matched with the prestored voiceprint features corresponding to the non-master users, establishing and storing the corresponding relation between the voiceprint features and the personal information corresponding to the voiceprint features.
5. The conversation assistance apparatus according to claim 4, wherein the information processing module further comprises: a prompt information sub-module and a command receiving sub-module, wherein,
the prompt information submodule is used for sending prompt information for judging whether the voice signal is stored or not if the voiceprint characteristics are not matched with the prestored voiceprint characteristics corresponding to the non-master user;
the command receiving sub-module is used for receiving a storage command of the main user and storing the voice signal.
6. The dialog assistance device of claim 1 wherein the information output module is a voice broadcast module or a brain-computer interface module.
7. The conversation assistance device of claim 1, wherein the conversation assistance device is a headset or a cell phone.
8. A method for obtaining information, the method comprising:
receiving a voice signal;
extracting voice characteristics corresponding to the voice signals;
judging whether the voice features are matched with pre-stored voice features corresponding to non-master users according to the voice features, wherein the non-master users are users who have a conversation with the master users, and the master users are users who wear the conversation auxiliary equipment;
if the voice features are matched with pre-stored voice features corresponding to non-master users, obtaining the personal information of the non-master users corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master users;
and sending the personal information of the non-master user to an information output module so that the information output module outputs the personal information of the non-master user.
9. The method of claim 8, wherein the voice feature comprises a voiceprint feature; and judging whether the voice features are matched with pre-stored voice features corresponding to non-master users or not according to the voice features, specifically judging whether the voiceprint features are matched with pre-stored voiceprint features corresponding to non-master users or not according to the voiceprint features.
10. The method of claim 9, wherein the speech features further include vocabulary features and/or prosodic features, and the personal information is emotion information; if the voice features are matched with the pre-stored voice features corresponding to the non-master user, obtaining the personal information of the non-master user corresponding to the voice features according to the corresponding relation between the pre-stored voice features and the personal information of the non-master user, and specifically, if the voiceprint features are matched with the pre-stored voiceprint features corresponding to the non-master user, obtaining the emotion information of the non-master user corresponding to the vocabulary features and/or the prosodic features according to the corresponding relation between the pre-stored vocabulary features and/or the prosodic features and the emotion information of the non-master user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058908.7A CN111179943A (en) | 2019-10-30 | 2019-10-30 | Conversation auxiliary equipment and method for acquiring information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911058908.7A CN111179943A (en) | 2019-10-30 | 2019-10-30 | Conversation auxiliary equipment and method for acquiring information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179943A true CN111179943A (en) | 2020-05-19 |
Family
ID=70655762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911058908.7A Pending CN111179943A (en) | 2019-10-30 | 2019-10-30 | Conversation auxiliary equipment and method for acquiring information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179943A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112002331A (en) * | 2020-08-05 | 2020-11-27 | 广州景瑞智能科技有限公司 | Method and system for recognizing emotion based on conversation voice |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001016940A1 (en) * | 1999-08-31 | 2001-03-08 | Accenture, Llp | System, method, and article of manufacture for a voice recognition system for identity authentication in order to gain access to data on the internet |
| CN101789990A (en) * | 2009-12-23 | 2010-07-28 | 宇龙计算机通信科技(深圳)有限公司 | Method and mobile terminal for judging emotion of opposite party in conservation process |
| CN102347060A (en) * | 2010-08-04 | 2012-02-08 | 鸿富锦精密工业（深圳）有限公司 | Electronic recording device and method |
| CN103258535A (en) * | 2013-05-30 | 2013-08-21 | 中国人民财产保险股份有限公司 | Identity recognition method and system based on voiceprint recognition |
| CN105895101A (en) * | 2016-06-08 | 2016-08-24 | 国网上海市电力公司 | Speech processing equipment and processing method for power intelligent auxiliary service system |
| US20180005464A1 (en) * | 2016-06-29 | 2018-01-04 | Ncr Corporation | Visual voucher communication systems and methods |
| CN108632475A (en) * | 2018-03-22 | 2018-10-09 | 平安科技（深圳）有限公司 | Voice leaving method, device, computer equipment and storage medium |
| CN109618068A (en) * | 2018-11-08 | 2019-04-12 | 上海航动科技有限公司 | A kind of voice service method for pushing, device and system based on artificial intelligence |
-
2019
- 2019-10-30 CN CN201911058908.7A patent/CN111179943A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001016940A1 (en) * | 1999-08-31 | 2001-03-08 | Accenture, Llp | System, method, and article of manufacture for a voice recognition system for identity authentication in order to gain access to data on the internet |
| CN101789990A (en) * | 2009-12-23 | 2010-07-28 | 宇龙计算机通信科技(深圳)有限公司 | Method and mobile terminal for judging emotion of opposite party in conservation process |
| CN102347060A (en) * | 2010-08-04 | 2012-02-08 | 鸿富锦精密工业（深圳）有限公司 | Electronic recording device and method |
| CN103258535A (en) * | 2013-05-30 | 2013-08-21 | 中国人民财产保险股份有限公司 | Identity recognition method and system based on voiceprint recognition |
| CN105895101A (en) * | 2016-06-08 | 2016-08-24 | 国网上海市电力公司 | Speech processing equipment and processing method for power intelligent auxiliary service system |
| US20180005464A1 (en) * | 2016-06-29 | 2018-01-04 | Ncr Corporation | Visual voucher communication systems and methods |
| CN108632475A (en) * | 2018-03-22 | 2018-10-09 | 平安科技（深圳）有限公司 | Voice leaving method, device, computer equipment and storage medium |
| CN109618068A (en) * | 2018-11-08 | 2019-04-12 | 上海航动科技有限公司 | A kind of voice service method for pushing, device and system based on artificial intelligence |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112002331A (en) * | 2020-08-05 | 2020-11-27 | 广州景瑞智能科技有限公司 | Method and system for recognizing emotion based on conversation voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107623614B (en) | Method and device for pushing information | |
| US20150348538A1 (en) | Speech summary and action item generation | |
| JP2023022150A (en) | Bidirectional speech translation system, bidirectional speech translation method and program | |
| JP5311348B2 (en) | Speech keyword collation system in speech data, method thereof, and speech keyword collation program in speech data | |
| CN108922525B (en) | Voice processing method, device, storage medium and electronic equipment | |
| US20100250249A1 (en) | Communication control apparatus, communication control method, and computer-readable medium storing a communication control program | |
| CN104811559A (en) | Noise reduction method, communication method and mobile terminal | |
| WO2017085992A1 (en) | Information processing apparatus | |
| US20220231873A1 (en) | System for facilitating comprehensive multilingual virtual or real-time meeting with real-time translation | |
| US11699043B2 (en) | Determination of transcription accuracy | |
| JP2009178783A (en) | Communication robot and its control method | |
| CN104851423B (en) | Sound information processing method and device | |
| JP6268916B2 (en) | Abnormal conversation detection apparatus, abnormal conversation detection method, and abnormal conversation detection computer program | |
| JP6599828B2 (en) | Sound processing method, sound processing apparatus, and program | |
| CN110545504A (en) | Personal hearing device, external sound processing device and related computer program product | |
| CN111179943A (en) | Conversation auxiliary equipment and method for acquiring information | |
| JP2019015837A (en) | Conversation type robot having character of cat and conversation management program for showing character of cat | |
| KR102000282B1 (en) | Conversation support device for performing auditory function assistance | |
| CN113299309A (en) | Voice translation method and device, computer readable medium and electronic equipment | |
| JP2004252085A (en) | System and program for voice conversion | |
| JP2007259427A (en) | Mobile terminal unit | |
| KR100553437B1 (en) | wireless telecommunication terminal and method for transmitting voice message using speech synthesizing | |
| CN115240689B (en) | Target sound determination method, target sound determination device, computer equipment and medium | |
| JP7110057B2 (en) | speech recognition system | |
| KR20180034927A (en) | Communication terminal for analyzing call speech |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |
|
| RJ01 | Rejection of invention patent application after publication |