GB2326490A - Voice activated control system and method - Google Patents

Voice activated control system and method Download PDF

Info

Publication number
GB2326490A
GB2326490A GB9712962A GB9712962A GB2326490A GB 2326490 A GB2326490 A GB 2326490A GB 9712962 A GB9712962 A GB 9712962A GB 9712962 A GB9712962 A GB 9712962A GB 2326490 A GB2326490 A GB 2326490A
Authority
GB
United Kingdom
Prior art keywords
voice command
input voice
input
attribute
control system
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
Application number
GB9712962A
Other versions
GB9712962D0 (en
Inventor
Dave Jarvis
Gordon Freedman
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Microsemi Semiconductor ULC
Original Assignee
Mitel Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Mitel Corp filed Critical Mitel Corp
Priority to GB9712962A priority Critical patent/GB2326490A/en
Publication of GB9712962D0 publication Critical patent/GB9712962D0/en
Priority to CA 2240459 priority patent/CA2240459A1/en
Publication of GB2326490A publication Critical patent/GB2326490A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16Sound input; Sound output
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

A voice activated control system 10 includes a microphone 12 into which a voice command is inputted. A speech recognition unit 14 coupled to the microphone recognizes the input voice command when it corresponds with a voice command stored therein. A voice command attribute detector 16 is also coupled to the microphone and detects the value of a parameter of at least one attribute of the input voice command, for example its volume or the pitch. A controller 20 is responsive to the speech recognition unit 14 and voice command attribute detector 16 when the input voice command is recognized, and executes an operation associated with the recognised input voice command. The controller varies the execution of the operation in accordance with the value of the detected parameter of the at least one attribute. The system can be used to control a drawing package on a PC, or in appliances such as stereos, light dimmers etc.

Description

VOICE ACTIVATED CONTROL SYSTEM AND METHOD Field Of The Invention The present invention relates to control systems and in particular to a voice activated control system and method to allow input voice commands to be used to initiate execution of an operation and to vary the execution of the operation.
Background Of The Invention Voice activated control systems to allow input voice commands to be used to initiate execution of an operation are known in the art. For example, U.S.
Patent No. 4,704,696 to Reimer et al discloses a video game responsive to voice commands to obviate the need for a joystick. The video game partitions input voice commands and determines the frequency content of the input voice command in the various partitions. The determined frequencies in the various partitions are compared with stored data in the video game to determine if the input voice command corresponds with a voice command stored in memory within the video game. If a correlation occurs, the video game executes an operation corresponding to the input voice command to alter game play.
U.S. Patent No. 5,220,639 to Lee discloses a Mandarin speech recognition machine which can be trained to recognize different tones of syllable utterances to facilitate correlation of an uttered tone with corresponding tones stored in memory within the speech recognition machine. This allows spoken syllables and tones to be recognized in order to distinguish Mandarin speech. Recognized sentences are converted into Chinese characters and displayed on a computer screen.
U.S. Patent No. 5,345,538 to Narayannan et al discloses a speech recognition system for controlling movement of a microscope in response to detected input voice commands. Different input voice commands cause similar movements of the microscope at different rates. Input voice commands exceeding a threshold level cause the system to stop movement of the microscope regardless of whether the input voice command is recognized.
Although the above-described references disclose voice command recognition systems for detecting and recognizing input voice commands and executing operations in response to the recognized voice commands, these prior art systems are limited in that the executed operations are preset and are based solely on the recognized voice commands themselves regardless of variations in the manner in which the voice commands are spoken. As such, quantitative variances in the executed operations are not possible.
It is therefore an object of the present invention to provide a novel voice activated control system and method which obviate or mitigate at least one of the disadvantages associated with the prior art.
Summarv Of The Invention According to one aspect of the present invention there is provided a voice activated control system comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone and recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a voice command attribute detector detecting the value of a parameter of at least one attribute of said input voice command; and a controller responsive to said speech recognition unit and said voice command attribute detector when said input voice command is recognized and executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
In one embodiment, the voice command attribute detector detects the volume level of the input voice command. In another embodiment, the voice command attribute detector detects the tone of the input voice command. The voice activated control system can be used to control an appliance or altematively to modify the execution of software.
According to another aspect of the present invention there is provided a voice activated control system comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone for recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a volume and/or tone detector for detecting the volume level and/or tone of said input voice command; and a controller responsive to said speech recognition unit and said volume and/or tone detector when said input voice command is recognized and executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the detected volume level and/or tone of said input voice command.
According to still yet another aspect of the present invention there is provided a method of controlling the execution of an operation associated with an input voice command, said method comprising the steps of: comparing an input voice command with stored voice commands and recognizing said input voice command when a match occurs; detecting the value of a parameter of at least one attribute of said recognized input voice command; and executing an operation associated with said recognized input voice command when a match occurs, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
According to still yet another aspect of the present invention there is provided a control system for an appliance comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone for recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a voice command attribute detector for detecting the value of a parameter of at least one attribute of said input voice command; and a controller responsive to said speech recognition unit and said voice command attribute detector when said input voice command is recognized and executing an operation associated with said recognized input voice command to control said appliance, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
According to still yet another aspect of the present invention there is provided a computer readable media encoded with a computer program for controlling the execution of an operation comprising: means for recognizing an input voice command when said input voice command corresponds to a stored voice command; means for detecting the value of a parameter of at least one attribute of said input voice command; and means for executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
The present invention provides advantages in that input voice commands and attributes of the input voice commands such as for example volumes and/or tones can be used to control the operation of an output device. This allows quantitative variances in the execution of operations associated with the input voice commands to be achieved by changing the volume and/or tone of input voice commands.
Brief Description Of The Drawings Embodiments of the present invention will now be described more fully with reference to the accompanying drawings in which: Figure 1 is a block diagram of a voice activated control system in accordance with the present invention; Figure 2 is a block diagram of a speech recognition unit forming part of the voice activated control system of Figure 1; Figure 3 is a block diagram of a voice command attribute detector forming part of the voice activated control system of Figure 1; and Figure 4 is a block diagram of a controller forming part of the voice activated control system of Figure 1.
Detailed Description Of The Preferred Embodiments Referring now to Figure 1, a voice activated control system (VACS) to allow input voice commands to be detected and used to control the operation of an output device is shown and is generally indicated to by reference numeral 10. As can be seen, the VACS 10 includes a microphone 12 into which voice commands are input. Coupled to the microphone 12 is a speech recognition unit 14 and a voice command attribute detector 16. Speech recognition unit 14 analyses voice commands input into the microphone 12 to determine if entered voice commands correspond to voice commands stored in memory therein. The voice command attribute detector 16 analyses input voice commands to determine the value of a parameter of at least one attribute of the input voice command such as for example, the volume level or tone of the input voice command. In this particular embodiment, the voice command attribute detector 16 detects the volume level of the input voice command. A controller 20 is responsive to the speech recognition unit 14 and to the voice command attribute detector 16 when an input voice command is recognized and executes an operation to control the output device in accordance with the detected input voice command and the detected volume level of the input voice command.
Referring now to Figure 2, the speech recognition unit 14 is better illustrated. The speech recognition unit may be of any conventional type which can be trained to recognize selected input voice commands such as that sold by Lyrix or alternatively can be built using a tool kit of subroutines such as Apples Computers Speech Recognition Manager. In this embodiment, the speech recognition unit 14 includes a speech analyzer 30 for detecting syllables and extracting features of an input voice command and for generating a digital signature representing the input voice command. A comparator 32 is coupled to the speech analyzer 30 and to memory in which a voice command library 34 is stored. The comparator 34 compares the generated digital signature with digital signatures stored in the voice command library 34 which represent valid voice commands recognizable by the speech recognition unit 14. If a match is detected, the comparator 34 conveys the digital signature to the controller 20.
Figure 3 better illustrates the voice command attribute detector 16. As can be seen, the voice command attribute detector includes a fast fourier transformer 40 to perform a fast fourier transform on the input voice command and thereby separate the input voice command into its frequency components. An averager 42 is in communication with the fast fourier transformer 40 and determines the mean amplitude of the frequency components to generate an "average" volume level of the input voice command. A digitizer 44 is connected to the averager 42 to convert the average volume level into a digital value.
The controller 20 is best illustrated in Figure 4 and includes memory storing an operations library 50 as well as a processor 52 for selecting and executing operations from the operations library 50. Specifically, the processor 52 selects operations from the operating library 50 which are associated with the digital signatures received from the speech recognition unit 14. The digital values received from the voice command attribute detector 16 are used by the processor 52 during execution of the selected operations, to determine the extent of the executed operations.
Preferably, the speech recognition unit 14, the voice command attribute detector 16 and the controller 20 are implemented in software executed by a personal computer or the like. It should however, be appreciated by those of skill in the art that if desired, the speech recognition unit, the voice command attribute detector and the controller can be constituted by discrete components.
The general operation of the VACS 10 will now be described. When a voice command is input into the microphone 12, the speech recognition unit 14 analyses the input voice command to determine if the input voice command corresponds to a voice command stored in the voice command library 34. At the same time, the voice command attribute detector 16 analyses the input voice command to determine the average volume level of the input voice command. If the input voice command does not correspond with a voice command stored in the voice command library, the input voice command is ignored.
If the input voice command corresponds with a voice command stored in the voice command library 34, the controller 20 receives the digital signature from the speech recognition unit 14 and selects the operation in the operations library 50 corresponding to received digital signature. The controller 20 also receives the digital volume level from the command attribute detector 16 and uses the digital value to establish the value of a parameter of the selected operation. Once the value of the parameter has been determined, the processor 52 executes the selected operation to control the output device. Thus, when an input voice command is input into the microphone 12, two variables, namely the input voice command itself and the value of the average volume level of the input voice command, are used during execution of an operation. In many environments, this allows two actions to be performed simultaneously which otherwise would be required to be performed individually.
The VACS 10 is useful in many environments such as in computer systems where the execution of commands can be controlled by input voice commands. For example, the VACS 10 can be incorporated into or used in conjunction with a drawing software program such as for example Corel DrawO. As is well known to those of skill in the art, drawing software programs of this nature include selectable icons representing geometrical shapes which can be drawn on a palette. When one of these icons is selected, the geometrical shape is drawn on the pallet when the cursor is dragged across the palette. The extent to which the cursor is dragged determines the size of the drawn geometrical shape. As will be appreciated, the drawing of the geometrical shape on the palette requires two distinct and separate operations to be performed, namely selection of the icon and then dragging of the cursor across the palette to size the geometrical shape being drawn.
When the VACS 10 is incorporated into such a drawing software program, an input voice command is used to select and draw the desired geometrical shape. The volume level of the input voice command is used to determine the size of the drawn geometrical shape.
In this embodiment, the speech recognition unit 14 is trained to recognize input voice commands corresponding to geometrical shapes and lines as well as actions associated with moving drawn shapes and/or lines. The voice command library 34 includes a command vocabulary comprising of the voice commands "circle", "square", "ellipse", "rectangle", "spiral", "line", "up", "down", "left", "right", "rotate" etc. This list of voice commands in the voice command library 34 is presented for illustrative purposes only. It should be apparent to one of skill in the art, that more or fewer voice commands can be included in the voice command library.
During execution of the VACS 10 in conjunction with the drawing software program, when a user inputs a voice command such as for example "circle" into the microphone 12, and the voice command is recognized by the speech recognition unit 14, the controller 20 executes an operation resulting in a circle being drawn on the palette. However before doing so, the controller 20 uses the detected volume level of the input voice command to establish the diameter of the drawn circle. Thus, a softly spoken "circle" input voice command will result in a small circle being drawn, while a loudly spoken "circle" input voice command will result in a large circle being drawn. A similar process is performed when other voice commands representing geometrical shapes and lines are input into the microphone 12.
With respect to voice commands representing actions, the detected volume level determines the extent of the action performed. For example, a softly spoken "rotate" input voice command will result in a selected drawn object being rotated about a selected axis by a small amount while a loudly spoken "rotate" input voice command will result in the selected object being rotated by a larger amount.
As one will appreciate, the VACS 10 can also be used in a Windows environment to allow input voice commands to be used to open, size and move windows.
The VACS 10 is also useful in appliances and other consumer products such as for example in stereos, light dimmers, power window controllers etc. In the case of stereos, the VACS 10 can be used to turn a stereo on and/or change the volume of the stereo. In the case of light dimmers and power window controllers, the VACS 10 can be used to change the illuminance of the light or position of the windows.
Although the VACS 10 has been described as detecting the volume level of the input voice command to vary the execution of the operation, other attributes of the input voice command such as for example tone may be used to vary the execution of the operation. Also, if desired the VACS 10 may include both volume level and pitch detectors. Those of skill in the art will appreciate that the present invention can be used in many applications and although particular embodiments have been described, it should be realized that variations and modifications may be made to the present invention without departing from the spirit and scope thereof as defined by the appended claims.

Claims (20)

We Claim:
1. A voice activated control system comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone and recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a voice command attribute detector detecting the value of a parameter of at least one attribute of said input voice command; and a controller responsive to said speech recognition unit and said voice command attribute detector when said input voice command is recognized and executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
2. A voice activated control system as defined in claim 1 wherein said voice command attribute detector includes a volume detector for detecting the volume level of said input voice command.
3. A voice activated control system as defined in claim 1 wherein said voice command attribute detector includes a pitch detector for detecting the tone of said input voice command.
4. A voice activated control system as defined in claim 1 wherein said voice command attribute detector includes a volume detector and a pitch detector.
5. A voice activated control system as defined in claim 1 wherein said controller controls the operation of an appliance during execution of said operation.
6. A voice activated control system as defined in claim 1 wherein said controller modifies the execution of software during execution of said operation.
7. A voice activated control system comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone for recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a volume and/or pitch detector for detecting the volume level and/or tone of said input voice command; and a controller responsive to said speech recognition unit and said volume and/or pitch detector when said input voice command is recognized and executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the detected volume level and/or tone of said input voice command.
8. A voice activated control system as defined in claim 7 wherein said controller controls the operation of an appliance during execution of said operation.
9. A voice activated control system as defined in claim 7 wherein said controller modifies the execution of software during execution of said operation.
10. A method of controlling the execution of an operation associated with an input voice command, said method comprising the steps of: comparing an input voice command with stored voice commands and recognizing said input voice command when a match occurs; detecting the value a parameter of at least one attribute of said recognized input voice command; and executing an operation associated with said recognized input voice command when a match occurs, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
11. The method of claim 10 wherein at said detecting step, the volume level of said input voice command is detected.
12. The method of claim 10 wherein at said detecting step, the tone of said input voice command is detected.
13. The method of claim 10 wherein at said detecting step, the volume level and tone of said input voice command are detected.
14. A control system for an appliance comprising: a microphone into which a voice command is input; a speech recognition unit coupled to said microphone for recognizing an input voice command when said input voice command corresponds to a voice command stored therein; a voice command attribute detector for detecting the value of a parameter of at least one attribute of said input voice command; and a controller responsive to said speech recognition unit and said voice command attribute detector when said input voice command is recognized and executing an operation associated with said recognized input voice command to control said appliance, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
15. A control system as defined in claim 14 wherein said voice command attribute detector includes a volume detector for detecting the volume level of said input voice command.
16. A control system as defined in claim 14 wherein said voice command attribute detector includes a pitch detector for detecting the tone of said input voice command.
17. A control system as defined in claim 14 wherein said voice command attribute detector includes a volume detector and a pitch detector.
18. A computer readable media encoded with a computer program for controlling the execution of an operation comprising: means for recognizing an input voice command when said input voice command corresponds to a stored voice command; means for detecting the value of a parameter of at least one attribute of said input voice command; and means for executing an operation associated with said recognized input voice command, variances in the execution of said operation being determined by the value of the detected parameter of said at least one attribute.
19. A computer readable media as defined in claim 18 wherein said detecting means detects the volume level of said input voice command.
20. A computer readable media as defined in claim 18 wherein said detecting means detects the tone of said input voice command.
GB9712962A 1997-06-19 1997-06-19 Voice activated control system and method Pending GB2326490A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GB9712962A GB2326490A (en) 1997-06-19 1997-06-19 Voice activated control system and method
CA 2240459 CA2240459A1 (en) 1997-06-19 1998-06-12 Voice activated control system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB9712962A GB2326490A (en) 1997-06-19 1997-06-19 Voice activated control system and method

Publications (2)

Publication Number Publication Date
GB9712962D0 GB9712962D0 (en) 1997-08-27
GB2326490A true GB2326490A (en) 1998-12-23

Family

ID=10814588

Family Applications (1)

Application Number Title Priority Date Filing Date
GB9712962A Pending GB2326490A (en) 1997-06-19 1997-06-19 Voice activated control system and method

Country Status (1)

Country Link
GB (1) GB2326490A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1063637A1 (en) * 1999-06-21 2000-12-27 Matsushita Electric Industrial Co., Ltd. Voice-actuated control apparatus and method of control using the same
US6912500B2 (en) * 2001-01-29 2005-06-28 Hewlett-Packard Development Company, L.P. Facilitation of speech recognition in user interface
US6970824B2 (en) 2000-12-05 2005-11-29 Hewlett-Packard Development Company, L.P. Enabling voice control of voice-controlled apparatus using a head mounted camera system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5220639A (en) * 1989-12-01 1993-06-15 National Science Council Mandarin speech input method for Chinese computers and a mandarin speech recognition machine
EP0653701A1 (en) * 1993-11-15 1995-05-17 International Business Machines Corporation Method and system for location dependent verbal command execution in a computer based control system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5220639A (en) * 1989-12-01 1993-06-15 National Science Council Mandarin speech input method for Chinese computers and a mandarin speech recognition machine
EP0653701A1 (en) * 1993-11-15 1995-05-17 International Business Machines Corporation Method and system for location dependent verbal command execution in a computer based control system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1063637A1 (en) * 1999-06-21 2000-12-27 Matsushita Electric Industrial Co., Ltd. Voice-actuated control apparatus and method of control using the same
US6970824B2 (en) 2000-12-05 2005-11-29 Hewlett-Packard Development Company, L.P. Enabling voice control of voice-controlled apparatus using a head mounted camera system
US6912500B2 (en) * 2001-01-29 2005-06-28 Hewlett-Packard Development Company, L.P. Facilitation of speech recognition in user interface

Also Published As

Publication number Publication date
GB9712962D0 (en) 1997-08-27

Similar Documents

Publication Publication Date Title
KR100457509B1 (en) Communication terminal controlled through a touch screen and a voice recognition and instruction executing method thereof
KR100354365B1 (en) Speech command input recognition system for interactive computer display with interpretation of ancillary relevant speech query terms into commands
US8942985B2 (en) Centralized method and system for clarifying voice commands
US6519566B1 (en) Method for hands-free operation of a pointer
KR100586286B1 (en) Eye gaze for contextual speech recognition
US9081590B2 (en) Multimodal input using scratchpad graphical user interface to edit speech text input with keyboard input
US5873064A (en) Multi-action voice macro method
KR102411619B1 (en) Electronic apparatus and the controlling method thereof
US6778191B2 (en) Method of interacting with a consumer electronics system
JP2000200094A (en) Method and device for displaying feedback on display
US20020123894A1 (en) Processing speech recognition errors in an embedded speech recognition system
US20020178005A1 (en) System and method for adaptive language understanding by computers
EP2017828A1 (en) Techniques for disambiguating speech input using multimodal interfaces
CN111627436B (en) Voice control method and device
EP1650744A1 (en) Invalid command detection in speech recognition
US5870705A (en) Method of setting input levels in a voice recognition system
CN110968245B (en) Operation method for controlling office software through voice
CN111161731A (en) Intelligent off-line voice control device for household electrical appliances
US5933807A (en) Screen control apparatus and screen control method
GB2326490A (en) Voice activated control system and method
CA2240459A1 (en) Voice activated control system and method
EP2757557A1 (en) Electronic apparatus and voice processing method thereof
US20060149545A1 (en) Method and apparatus of speech template selection for speech recognition
JP3744161B2 (en) Voice instruction device and voice instruction information storage medium
JP2003263308A (en) Screen control device and method

Legal Events

Date Code Title Description
732E Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)