Control center for a voice controlled wireless communication device system

• US 8,775,189 B2
• Filed: 08/09/2006
• Issued: 07/08/2014
• Est. Priority Date: 08/09/2005
• Status: Expired due to Fees

• Current Assignee: Mobile Voice Control LLC
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Burns, Stephen S., Kowitz, Mickey W.
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US11/501,950
• Publication Number:
  US 20070156411A1
• Time in Patent Office: 2,890 Days
• Field of Search: 704/231, 704/235, 704/241, 704/246, 704/251, 704/270, 704/270.1, 704/275, 379/88.01, 705/8, 705/9
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A wireless communication device is disclosed that accepts recorded audio data from an end-user. The audio data can be in the form of a command requesting user action. Likewise, the audio data can be converted into a text file. The audio data is reduced to a digital file in a format that is supported by the device hardware, such as a .wav, .mp3, .vnf file, or the like. The digital file is sent via secured or unsecured wireless communication to one or more server computers for further processing. In accordance with an important aspect of the invention, the system evaluates the confidence level of the of the speech recognition process. If the confidence level is high, the system automatically builds the application command or creates the text file for transmission to the communication device. Alternatively, if the confidence of the speech recognition is lower, the recorded audio data file is routed to a human transcriber employed by the telecommunications service, who manually reviews the digital voice file and builds the application command or text file. Once the application command is created, it is transmitted to the communication device. As a result of the present invention, speech recognition in the context of a communications devices has been shown to be accurate over 90% of the time.

Claims

1. A control center for receiving voice control commands from a wireless communication device, the control center configured to perform a method comprising:

receiving one or more recorded voice commands communicated from the wireless communication device and in response to a confidence level, the confidence level obtained from a server-based speech recognition program to yield an interpreted voice command file, directing the interpreted voice command file to a transcription interface corresponding to one or more human transcribers;

establishing a threshold confidence level, the threshold confidence level based on a confidence measurement from the server-based speech recognition program and indicating additional processing due to insufficient confidence in a result from the speech recognition program;

selectively directing, if an obtained confidence level is below the threshold confidence level, each of the voice commands from the one or more commands to a specific human transcriber interface from the one or more human transcribers interfaces based on a priority of the command, wherein the priority of the command is based on which command of the one or more commands requires an immediate response by the determination of the type of command received of the one or more commands;

receiving, from an interface of the specific human transcriber or from the speech recognition program based on the confidence level, an xml-based machine readable command file, to be communicated back to the wireless communication device; and

the xml-based machine readable command file indicative of a proper application for execution.

2. The control center in claim 1 wherein the voice command is directed to a specific human transcriber based on the volume of calls a particular transcriber has received.

3. The control center in claim 1 wherein the voice command is directed to a specific human transcriber based on the user who created the voice command.

4. The control center in claim 1 wherein the voice command is directed to a specific human transcriber based on the type of command.

5. The control center in claim 1 wherein the human transcriber updates the speech recognition program with the device user'"'"'s pronunciation of words that were not properly translated by the server-based speech recognition program.

6. The control center of claim 1 wherein the method further comprises:

setting a predefined level corresponding to the obtained confidence level;

creating, if the received confidence level is at or above the predefined level, the application commands using the recorded voice commands; and

routing, if the received confidence level is below the predefined level, the recorded voice commands for manual creation of the application commands.

7. The control center of claim 6 wherein the method further comprises:

routing based on a confidence level below the confidence threshold, and manually creating the application commands, wherein creating occurs following obtaining the confidence level and comparing to the threshold confidence level.

8. The control center of claim 1 wherein the method further comprises adjusting the threshold confidence level to a predefined level.

9. A set of processor based instructions stored on a non-transitory computer readable storage medium that, when executed by a computer, performs a method of receiving voice control commands from a wireless communication device comprising:

receiving, from a control center having the stored instructions and responsive to a wireless communication device, one or more recorded voice commands communicated from the wireless communication device and in response to a confidence level, the confidence level obtained from a server-based speech recognition program to yield an interpreted voice command file, directing the interpreted voice command file to a transcription interface corresponding to one or more human transcribers;

establishing a threshold confidence level, the threshold confidence level based on a confidence measurement from the server-based speech recognition program and indicating additional processing due to insufficient confidence in a result from the speech recognition program;

selectively directing, if an obtained confidence level is below the threshold confidence level, each of the voice commands from the one or more commands to a specific human transcriber interface from the one or more human transcriber interfaces based on a priority of the command, wherein the priority of the command is based on which command of the one or more commands requires an immediate response by the determination of the type of command received of the one or more commands;

receiving, from an interface of specific human transcriber or from the speech recognition program based on the confidence level, an xml-based machine readable command file; and

the xml-based machine readable command file including one or more application commands to be communicated back to the communication device, the xml-based machine readable command file indicative of a proper application for execution.

10. A method for interpreting voice commands from a wireless device responsive to a user by server side speech recognition program, comprising:

receiving a voice command by a speech recognition program from a wireless interface to the wireless device, the speech recognition program resident on a server responsive to the wireless device for delegation of speech recognition to the server, the speech recognition program yielding an interpreted voice command file;

determining if the speech recognition program attains a sufficient likelihood of an accurate recognition of a voice command by comparing a confidence level received from the speech recognition program to a threshold confidence level, the threshold confidence level for identifying a need for additional processing;

based on an identified need from an obtained confidence level below the threshold confidence level, identifying a transcription interface to a transcription process for completing recognition of the voice command in the event of inaccurate recognition by the speech recognition program, and

invoking the identified transcription interface, if the confidence level indicates a need for further processing for creating an xml-based machine readable command to be communicated back to the wireless communication device, including directing the received voice command to a specific human transcriber interface based on a priority of the command, wherein the priority of the command is based on which command of the one or more commands requires an immediate response by the determination of the type of command received, the xml-based machine readable command file indicative of a proper application for execution.

11. The method of claim 10 further comprising:

receiving the voice command by a plurality of speech recognition programs at the server, each of the speech recognition programs returning a corresponding confidence level in response to the voice command;

comparing each of the confidence levels to the threshold confidence level, and if multiple confidence levels attain the threshold confidence level; and

selecting, from among the confidence levels exceeding the threshold confidence level, the highest confidence level.

12. The method of claim 11 further comprising:

identifying a plurality of transcription interfaces for completing recognition of the voice command, each of the transcription interfaces having transcriber criteria indicative of an ability to generate application commands corresponding to the received voice commands;

selecting one of the transcription interfaces based on the transcriber criteria and the voice command; and

forwarding the voice command to the selected transcription interface to invoke the transcription interface.

13. The method of claim 12 wherein the transcriber criteria indicates at least one of least burdened, command type, typing volume of the application command, previous commands from the same user and identified dialect of the voice command.