CN112637139A - Voice transmission processing method and device based on Internet of things and computer equipment - Google Patents
Voice transmission processing method and device based on Internet of things and computer equipment Download PDFInfo
- Publication number
- CN112637139A CN112637139A CN202011430705.9A CN202011430705A CN112637139A CN 112637139 A CN112637139 A CN 112637139A CN 202011430705 A CN202011430705 A CN 202011430705A CN 112637139 A CN112637139 A CN 112637139A
- Authority
- CN
- China
- Prior art keywords
- information
- voice
- transmitted
- fundamental tone
- target
- 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.)
- Withdrawn
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 103
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 47
- 238000012360 testing method Methods 0.000 claims description 32
- 238000012937 correction Methods 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000011076 safety test Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1083—In-session procedures
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Telephonic Communication Services (AREA)
Abstract
According to the voice transmission processing method, device and computer equipment based on the Internet of things, the target voice information is accurately determined according to the text information, the target voice information is extracted, and the voice feature information can be timely and effectively extracted. And secondly, the extracted voice characteristic information is coded, so that the voice characteristic information can be conveniently searched, and the voice information to be transmitted can be accurately extracted from the target voice information according to the obtained name coding field. The voice information to be transmitted is extracted and then transmitted, whether interference factors exist in voice signals in the voice information to be transmitted or not is detected in the transmission process, so that the transmission quality is ensured, if the interference factors exist, the transmission of the voice information to be transmitted is stopped, the condition that the quality is unstable in the transmission process is avoided, the voice information to be transmitted is corrected, and the transmission quality can be ensured when the subsequent voice information to be transmitted is transmitted.
Description
Technical Field
The present disclosure relates to the field of voice transmission technologies, and in particular, to a voice transmission processing method and apparatus based on the internet of things, and a computer device.
Background
The instant messaging technology is a communication technology developed based on the internet and a mobile communication network, can realize communication in modes of videos, texts, short messages, voice and the like, and is popular among users.
With the development of the internet of things, voice transmission based on a physical network is gradually approved by users, most of the existing voice transmission technologies based on the physical network carry out voice transmission through bluetooth, and when an internet of things terminal (such as a mobile phone) moves, under the condition that the connection state of the bluetooth is unstable, how to ensure the quality of the voice transmission is a technical problem to be solved at the present stage.
Disclosure of Invention
In order to solve the technical problems in the related art, the present disclosure provides a voice transmission processing method and apparatus based on the internet of things, and a computer device.
The invention provides a voice transmission processing method based on the Internet of things, which comprises the following steps:
receiving a voice transmission instruction; the voice transmission instruction comprises a transmission mode label and a transmission path label;
if the transmission path label is matched with the path label corresponding to the transmission mode label, searching the text information corresponding to the transmission path label in a preset incidence relation set; the incidence relation set comprises incidence relations between the path labels and the voice information;
determining corresponding target voice information according to the text information;
acquiring a plurality of sections of voice characteristic information to be transmitted from target voice information, and carrying out voice coding processing on the voice characteristic information to obtain a name coding field;
when the name coding field indicates that the voice feature information contains a feature parameter label, extracting the voice information to be transmitted from the target voice information according to the voice feature information corresponding to the feature parameter label;
and transmitting the voice information to be transmitted according to the voice transmission instruction, detecting whether an interference factor exists in a voice signal in the voice information to be transmitted in the transmission process, if so, stopping transmitting the voice information to be transmitted, correcting the voice information to be transmitted and then continuing to transmit, and if not, continuing to transmit the voice information to be transmitted.
In an alternative embodiment of the method according to the invention,
the acquiring of multiple pieces of voice feature information to be transmitted from the target voice information specifically includes: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted;
the performing speech coding processing on the speech feature information to obtain a name coding field specifically includes: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
In an alternative embodiment, when the name coding field indicates that the voice feature information includes a feature parameter tag, extracting, according to the voice feature information corresponding to the feature parameter tag, the voice information to be transmitted from the target voice information, specifically including:
when the name coding field indicates that the voice feature information contains a feature parameter label, determining a label sequence corresponding to the feature parameter label in the target voice information;
extracting a plurality of continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet conditions;
and extracting the voice information to be transmitted in the current voice information based on preset indication extraction information.
In an alternative embodiment of the method according to the invention,
the detecting whether the voice signal in the voice information to be transmitted has an interference factor specifically includes: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor;
if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction tag to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
The invention provides a voice transmission processing device based on the Internet of things, which comprises the following functional modules:
the voice transmission instruction receiving module is used for receiving a voice transmission instruction; the voice transmission instruction comprises a transmission mode label and a transmission path label;
the text information searching module is used for searching text information corresponding to the transmission path label in a preset incidence relation set if the transmission path label is matched with the path label corresponding to the transmission mode label; the incidence relation set comprises incidence relations between the path labels and the voice information;
the target voice information determining module is used for determining corresponding target voice information according to the text information;
the name coding field acquisition module is used for acquiring a plurality of sections of voice characteristic information to be transmitted from target voice information and carrying out voice coding processing on the voice characteristic information to obtain a name coding field;
the voice information extraction module to be transmitted is used for extracting the voice information to be transmitted from the target voice information according to the voice characteristic information corresponding to the characteristic parameter label when the name coding field indicates that the voice characteristic information contains the characteristic parameter label;
and the interference factor judging module is used for transmitting the voice information to be transmitted according to the voice transmission instruction, detecting whether an interference factor exists in a voice signal in the voice information to be transmitted in the transmission process, stopping transmitting the voice information to be transmitted if the interference factor exists, correcting the voice information to be transmitted and then continuing transmitting the voice information to be transmitted, and continuing transmitting the voice information to be transmitted if the interference factor does not exist.
In an alternative embodiment of the method according to the invention,
the name coding field obtaining module is specifically configured to: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted;
the name coding field obtaining module may be further configured to: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
In an alternative embodiment, the voice information extraction module to be transmitted is specifically configured to:
when the name coding field indicates that the voice feature information contains a feature parameter label, determining a label sequence corresponding to the feature parameter label in the target voice information;
extracting a plurality of continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet conditions;
and extracting the voice information to be transmitted in the current voice information based on preset indication extraction information.
In an alternative embodiment of the method according to the invention,
the interference factor determination module is specifically configured to: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor;
if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction tag to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
A third aspect of the invention provides a computer device comprising a processor and a memory in communication with each other, the processor being configured to retrieve a computer program from the memory and to implement the method of any of the first aspects by running the computer program.
A fourth aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed, implements the method of any one of the first aspects.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects.
The invention provides a voice transmission processing method, a voice transmission processing device and computer equipment based on the Internet of things. And secondly, extracting the voice information to be transmitted from the target language information according to the voice characteristic information corresponding to the characteristic parameter label contained in the name coding field. And finally, in the process of transmitting the voice information to be transmitted, checking whether the voice signal in the voice information to be transmitted has an interference factor.
Therefore, the target voice information is accurately determined according to the character information, the target voice information is further extracted, and the voice feature information can be timely and effectively extracted. And secondly, the extracted voice characteristic information is coded, so that the voice characteristic information can be conveniently searched, and the voice information to be transmitted can be accurately extracted from the target voice information according to the obtained name coding field. The voice information to be transmitted is extracted and then transmitted, in the transmission process, whether interference factors exist in voice signals in the voice information to be transmitted or not is detected, so that the transmission quality is ensured, if the interference factors exist, the transmission of the voice information to be transmitted is stopped, the condition that the quality is unstable in the transmission process is avoided, the voice information to be transmitted is further corrected, and the transmission quality can be ensured when the subsequent voice information to be transmitted is transmitted.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a flowchart of a voice transmission processing method based on the internet of things according to an embodiment of the present invention.
Fig. 2 is a block diagram of a voice transmission processing apparatus based on the internet of things according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Referring to fig. 1, an embodiment of the present invention provides a flowchart of a voice transmission processing method based on the internet of things, and the method specifically executes the contents described in the following steps S110 to S160.
Step S110, receiving a voice transmission instruction; in this embodiment, the voice transmission instruction includes a transmission mode tag and a transmission path tag.
Step S120, if the transmission path label is matched with the path label corresponding to the transmission mode label, searching the text information corresponding to the transmission path label in a preset incidence relation set; in this embodiment, the association set includes an association between a path tag and voice information.
And step S130, determining corresponding target voice information according to the character information.
Step S140, obtaining multiple pieces of voice feature information to be transmitted from the target voice information, and performing voice coding processing on the voice feature information to obtain a name coding field.
Step S150, when the name coding field indicates that the voice feature information contains a feature parameter label, extracting the voice information to be transmitted from the target voice information according to the voice feature information corresponding to the feature parameter label.
Step S160, transmitting the voice information to be transmitted according to the voice transmission instruction, detecting whether an interference factor exists in a voice signal in the voice information to be transmitted during transmission, if so, stopping transmitting the voice information to be transmitted, correcting the voice information to be transmitted, and then continuing to transmit the voice information to be transmitted, and if not, continuing to transmit the voice information to be transmitted.
Executing the contents described in step S110 to step S160, first determining corresponding target voice information according to the found text information, and obtaining voice feature information from the target voice information, and further performing voice coding processing on the voice feature information to obtain a name coding field. And secondly, extracting the voice information to be transmitted from the target language information according to the voice characteristic information corresponding to the characteristic parameter label contained in the name coding field. And finally, in the process of transmitting the voice information to be transmitted, checking whether the voice signal in the voice information to be transmitted has an interference factor.
Therefore, the target voice information is accurately determined according to the character information, the target voice information is further extracted, and the voice feature information can be timely and effectively extracted. And secondly, the extracted voice characteristic information is coded, so that the voice characteristic information can be conveniently searched, and the voice information to be transmitted can be accurately extracted from the target voice information according to the obtained name coding field. The voice information to be transmitted is extracted and then transmitted, in the transmission process, whether interference factors exist in voice signals in the voice information to be transmitted or not is detected, so that the transmission quality is ensured, if the interference factors exist, the transmission of the voice information to be transmitted is stopped, the condition that the quality is unstable in the transmission process is avoided, the voice information to be transmitted is further corrected, and the transmission quality can be ensured when the subsequent voice information to be transmitted is transmitted.
In specific implementation, in order to timely and effectively acquire the voice feature information from the target voice information, the acquiring, from the target voice information, the multiple pieces of voice feature information to be transmitted described in step S140 specifically includes: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; and extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted.
By executing the content, firstly, the test label corresponding to the information characteristic queue at present is determined, so that effective information elements and/or invalid information elements in the information characteristic queue can be accurately determined subsequently according to the test label, further, the information safety test is carried out on the characteristic queue according to the information of the effective information elements and/or the invalid information elements, the target voice information can be prevented from being falsified by third-party information, and after the information safety test is carried out on the characteristic queue, the voice characteristic information can be timely and effectively obtained from the target voice information.
Further, in order to accurately obtain the name code field and avoid encoding the interference information during the speech encoding, the speech encoding processing on the speech feature information to obtain the name code field described in step S140 specifically includes: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
By executing the above contents, the key node information in the voice feature information is extracted at first, and the redundant processing is performed on the key node information, so that the key node information can be denoised, the interference information in the key node information is eliminated, then the redundant information is eliminated to obtain the residual information for voice coding processing, so that the name coding field can be accurately obtained, the interference information is prevented from being coded during voice coding, and the working efficiency is further improved.
In a specific implementation, in order to accurately extract the voice information to be transmitted, when the name coding field indicates that the voice feature information includes a feature parameter tag, the voice information to be transmitted is extracted from the target voice information according to the voice feature information corresponding to the feature parameter tag, which is described in step S150, and specifically includes the contents described in the following sub-steps S1501 to S1505:
step S1501, when the name coding field indicates that the voice feature information contains a feature parameter tag, determining a tag sequence corresponding to the feature parameter tag in the target voice information;
step S1502, extracting multiple continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
step S1503, acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
step S1504, determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet the conditions;
in step S1505, the voice information to be transmitted in the current voice information is extracted based on the preset indication extraction information.
Determining a tag sequence by executing the contents described in the above steps S1501 to S1505, extracting the voice identification information in the tag sequence, and extracting the target sequence of the target voice information based on the obtained target voice identification information, so that the document classification feature can be effectively determined. Therefore, the voice information to be transmitted can be accurately extracted.
In specific implementation, in order to detect whether there is an interference factor in the voice signal in the voice information to be transmitted in step S160, the method specifically includes: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; and if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor.
The method comprises the steps of executing the above contents, identifying the voice information to be transmitted according to a voice identification instruction, accurately obtaining a voice data section, determining a voice signal corresponding to the voice information to be transmitted based on the obtained voice data section, further comparing the voice signal in the voice information to be transmitted with a preset pitch frequency, and further judging whether the voice signal in the voice information to be transmitted has an interference factor, if the interference factor does not exist, the transmission quality of the voice information to be transmitted in the transmission process can be ensured, if the interference factor exists, the transmission of the voice information to be transmitted is stopped, the condition that the quality is unstable in the transmission process is avoided, further correcting the voice information to be transmitted, and ensuring the transmission quality when the subsequent voice information to be transmitted is transmitted.
Further, if the current pitch frequency of the speech signal is not matched with a preset pitch frequency, and pitch period data in the pitch frequency of the speech signal is smaller than preset data, adding a correction tag to be corrected to the speech signal in the to-be-transmitted speech information corresponding to the target speech information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
On the basis, please refer to fig. 2, an embodiment of the present invention further provides a voice transmission processing apparatus 200 based on the internet of things, which includes the following functional modules:
a voice transmission instruction receiving module 210, configured to receive a voice transmission instruction; the voice transmission instruction comprises a transmission mode label and a transmission path label;
a text information searching module 220, configured to search text information corresponding to the transmission path tag in a preset association set if the transmission path tag matches the path tag corresponding to the transmission mode tag; the incidence relation set comprises incidence relations between the path labels and the voice information;
a target voice information determining module 230, configured to determine, according to the text information, corresponding target voice information;
a name coding field obtaining module 240, configured to obtain multiple pieces of voice feature information to be transmitted from target voice information, and perform voice coding processing on the voice feature information to obtain a name coding field;
a to-be-transmitted voice information extraction module 250, configured to, when the name coding field indicates that the voice feature information includes a feature parameter tag, extract, according to the voice feature information corresponding to the feature parameter tag, to-be-transmitted voice information from the target voice information;
the interference factor determining module 260 is configured to transmit the voice information to be transmitted according to the voice transmission instruction, detect whether an interference factor exists in a voice signal in the voice information to be transmitted in a transmission process, stop transmitting the voice information to be transmitted if the interference factor exists, correct the voice information to be transmitted, and continue transmitting the voice information to be transmitted if the interference factor does not exist.
In an alternative embodiment, the name code field obtaining module 240 is specifically configured to: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted;
the name code field obtaining module 240 may be further configured to: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
In an alternative embodiment, the voice information extraction module 250 is specifically configured to:
when the name coding field indicates that the voice feature information contains a feature parameter label, determining a label sequence corresponding to the feature parameter label in the target voice information;
extracting a plurality of continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet conditions;
and extracting the voice information to be transmitted in the current voice information based on preset indication extraction information.
In an alternative embodiment, the interference factor determining module 260 is specifically configured to: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor;
if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction tag to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
On the basis of the above, please refer to fig. 3, the present invention further provides a computer device 300, which includes a processor 310, and a memory 320 and a bus 330 connected to the processor 310; wherein, the processor 310 and the memory 320 communicate with each other through the bus 330; the processor 310 is used to call the program instructions in the memory 320 to execute the above-mentioned method.
Further, a readable storage medium is provided, on which a program is stored, which when executed by a processor implements the method described above.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A voice transmission processing method based on the Internet of things is characterized by comprising the following steps:
receiving a voice transmission instruction; the voice transmission instruction comprises a transmission mode label and a transmission path label;
if the transmission path label is matched with the path label corresponding to the transmission mode label, searching the text information corresponding to the transmission path label in a preset incidence relation set; the incidence relation set comprises incidence relations between the path labels and the voice information;
determining corresponding target voice information according to the text information;
acquiring a plurality of sections of voice characteristic information to be transmitted from target voice information, and carrying out voice coding processing on the voice characteristic information to obtain a name coding field;
when the name coding field indicates that the voice feature information contains a feature parameter label, extracting the voice information to be transmitted from the target voice information according to the voice feature information corresponding to the feature parameter label;
and transmitting the voice information to be transmitted according to the voice transmission instruction, detecting whether an interference factor exists in a voice signal in the voice information to be transmitted in the transmission process, if so, stopping transmitting the voice information to be transmitted, correcting the voice information to be transmitted and then continuing to transmit, and if not, continuing to transmit the voice information to be transmitted.
2. The method of claim 1,
the acquiring of multiple pieces of voice feature information to be transmitted from the target voice information specifically includes: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted;
the performing speech coding processing on the speech feature information to obtain a name coding field specifically includes: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
3. The method according to claim 1, wherein when the name coding field indicates that the voice feature information includes a feature parameter tag, extracting the voice information to be transmitted from the target voice information according to the voice feature information corresponding to the feature parameter tag, specifically including:
when the name coding field indicates that the voice feature information contains a feature parameter label, determining a label sequence corresponding to the feature parameter label in the target voice information;
extracting a plurality of continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet conditions;
and extracting the voice information to be transmitted in the current voice information based on preset indication extraction information.
4. The method of claim 1,
the detecting whether the voice signal in the voice information to be transmitted has an interference factor specifically includes: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor;
if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction tag to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
5. The utility model provides a speech transmission processing apparatus based on thing networking which characterized in that, the device includes following functional module:
the voice transmission instruction receiving module is used for receiving a voice transmission instruction; the voice transmission instruction comprises a transmission mode label and a transmission path label;
the text information searching module is used for searching text information corresponding to the transmission path label in a preset incidence relation set if the transmission path label is matched with the path label corresponding to the transmission mode label; the incidence relation set comprises incidence relations between the path labels and the voice information;
the target voice information determining module is used for determining corresponding target voice information according to the text information;
the name coding field acquisition module is used for acquiring a plurality of sections of voice characteristic information to be transmitted from target voice information and carrying out voice coding processing on the voice characteristic information to obtain a name coding field;
the voice information extraction module to be transmitted is used for extracting the voice information to be transmitted from the target voice information according to the voice characteristic information corresponding to the characteristic parameter label when the name coding field indicates that the voice characteristic information contains the characteristic parameter label;
and the interference factor judging module is used for transmitting the voice information to be transmitted according to the voice transmission instruction, detecting whether an interference factor exists in a voice signal in the voice information to be transmitted in the transmission process, stopping transmitting the voice information to be transmitted if the interference factor exists, correcting the voice information to be transmitted and then continuing transmitting the voice information to be transmitted, and continuing transmitting the voice information to be transmitted if the interference factor does not exist.
6. The apparatus of claim 5,
the name coding field obtaining module is specifically configured to: processing the target voice information into an information characteristic queue, and determining a test label currently corresponding to the information characteristic queue; determining valid information elements and/or invalid information elements in the information characteristic queue based on the test tag; when a valid information element is determined, performing information security test on the information feature queue by adopting network environment information matched with the valid information element, and when an invalid information element is determined, performing information security test on the information feature queue by adopting network environment information not matched with the invalid information element; extracting voice feature information from the information feature queue according to the obtained test result and a preset feature extraction mode to obtain multiple sections of voice feature information to be transmitted;
the name coding field obtaining module may be further configured to: extracting key node information in the voice feature information for each section of the acquired voice feature information; performing redundancy processing on the key node information according to a preset redundancy processing mode, acquiring redundant information in the key node information after the redundancy processing, and removing the redundant information to obtain residual information; and carrying out voice coding processing on the residual information based on a pre-stored coding rule to obtain a name coding field.
7. The apparatus according to claim 5, wherein the to-be-transmitted speech information extraction module is specifically configured to:
when the name coding field indicates that the voice feature information contains a feature parameter label, determining a label sequence corresponding to the feature parameter label in the target voice information;
extracting a plurality of continuous voice identification information in the label sequence from the target voice information to obtain target voice identification information;
acquiring a target sequence of target voice information based on the target voice identification information, wherein the target sequence is generated when the target voice information is determined;
determining the document classification characteristics of the target sequence, and determining to indicate the target voice information as the current voice information to be extracted when the document classification characteristics meet conditions;
and extracting the voice information to be transmitted in the current voice information based on preset indication extraction information.
8. The apparatus of claim 5,
the interference factor determination module is specifically configured to: when a voice recognition instruction is detected, recognizing a voice data section in the voice information to be transmitted; determining a voice signal corresponding to the voice information to be transmitted based on the voice data segment; when the voice signal corresponding to the voice information to be transmitted is determined, judging whether the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency; if the current fundamental tone frequency of the voice signal is matched with a preset fundamental tone frequency, judging that the voice signal in the voice information to be transmitted has no interference factor; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction label needing to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information; if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency and the period weight of the fundamental tone period data in the fundamental tone frequency of the voice signal is greater than or equal to the preset weight, judging that the voice signal in the voice information to be transmitted has an interference factor;
if the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, and the fundamental tone period data in the fundamental tone frequency of the voice signal is smaller than the preset data, adding a correction tag to be corrected to the voice signal in the voice information to be transmitted corresponding to the target voice information, including: when the current fundamental tone frequency of the voice signal is not matched with the preset fundamental tone frequency, determining a data link layer corresponding to the voice information to be transmitted; when the transmission node of the target voice information corresponds to the node position of the data link layer, and the period weight of the pitch period data in the pitch frequency of the voice signal is smaller than the preset weight, determining the position of a correction label to be added according to the node position and the pitch period data; and adding a correction label to the voice signal in the voice information to be transmitted corresponding to the target voice information according to the determined position needing to be added with the correction label.
9. A computer device comprising a processor and a memory in communication with each other, the processor being configured to retrieve a computer program from the memory and to implement the method of any one of claims 1-4 by running the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when executed, implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430705.9A CN112637139A (en) | 2020-12-09 | 2020-12-09 | Voice transmission processing method and device based on Internet of things and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011430705.9A CN112637139A (en) | 2020-12-09 | 2020-12-09 | Voice transmission processing method and device based on Internet of things and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112637139A true CN112637139A (en) | 2021-04-09 |
Family
ID=75309033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011430705.9A Withdrawn CN112637139A (en) | 2020-12-09 | 2020-12-09 | Voice transmission processing method and device based on Internet of things and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112637139A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113923177A (en) * | 2021-09-30 | 2022-01-11 | 完美世界(北京)软件科技发展有限公司 | Voice processing system, method and device for instant messaging |
-
2020
- 2020-12-09 CN CN202011430705.9A patent/CN112637139A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113923177A (en) * | 2021-09-30 | 2022-01-11 | 完美世界(北京)软件科技发展有限公司 | Voice processing system, method and device for instant messaging |
| CN113923177B (en) * | 2021-09-30 | 2023-01-06 | 完美世界(北京)软件科技发展有限公司 | Voice processing system, method and device for instant messaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108881138B (en) | Webpage request identification method and device | |
| CN104181567B (en) | Terminal device positioning method, terminal device and terminal device positioning system | |
| CN114710224A (en) | Frame synchronization method and device, computer readable medium and electronic device | |
| CN111339137A (en) | Data verification method and device | |
| CN108234441B (en) | Method, apparatus, electronic device and storage medium for determining forged access request | |
| CN112637139A (en) | Voice transmission processing method and device based on Internet of things and computer equipment | |
| CN114448664A (en) | Phishing webpage identification method and device, computer equipment and storage medium | |
| CN111767543B (en) | Replay attack vulnerability determination method, device, equipment and readable storage medium | |
| KR101792204B1 (en) | Apparatus and method for analyzing voice phishing pattern based on probability | |
| CN111049724B (en) | Mail security check method, device, computer equipment and storage medium | |
| CN111737695A (en) | White list optimization method, device, equipment and computer readable storage medium | |
| CN109446052B (en) | Verification method and device for application program | |
| CN116112209A (en) | Vulnerability attack flow detection method and device | |
| CN115527520A (en) | Anomaly detection method, device, electronic equipment and computer readable storage medium | |
| CN104933061B (en) | character string detection method and device and electronic equipment | |
| CN114818716A (en) | Risk subject identification method and device, storage medium and equipment | |
| CN111125567B (en) | Equipment marking method, device, electronic equipment and storage medium | |
| CN115712887B (en) | Picture verification code identification method and device, electronic equipment and storage medium | |
| CN115167767B (en) | Dirty data prevention method and system based on BBC exclusive OR check | |
| CN114547628B (en) | Vulnerability detection method and device | |
| CN115065540B (en) | Method and device for detecting web vulnerability attack and electronic equipment | |
| CN114244581B (en) | Cache poisoning vulnerability detection method and device, electronic equipment and storage medium | |
| CN114338089B (en) | Anti-attack method, device, equipment and computer readable storage medium | |
| CN116524394B (en) | Video detection method, device, equipment and storage medium | |
| CN111859078B (en) | Information identification method and device and electronic equipment |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210409 |