Use of multiple speech recognition software instances

• US 7,822,610 B2
• Filed: 08/09/2006
• Issued: 10/26/2010
• Est. Priority Date: 08/09/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Mobile Voice Control LLC
• Inventors: Burns, Stephen S., Kowitz, Mickey W.
• Primary Examiner(s): Sked; Matthew J
• Application Number:
  US11/501,998
• Publication Number:
  US 20070156412A1
• Time in Patent Office: 1,539 Days
• Field of Search: None
• US Class Current: 704/270.1
• 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 method of using speech recognition software for recorded audio data received from a wireless communication device, comprising:

Receiving recorded audio data communicated from a wireless communication device and directing the audio data to more than one simultaneous servers running speech recognition software, wherein the number of simultaneous servers running speech recognition software receiving the same audio data is controlled by the communication device user'"'"'s options;

Receiving a confidence level of recognition from each server running speech recognition software;

Routing the recognition result with the highest confidence level for further processing;

wherein receiving a confidence level of recognition from each server running speech recognition software includes;

upon detecting that each confidence level of recognition from each server running speech recognition software is below a predefined level, routing the recorded audio data to a location associated with a human transcriber currently experiencing an acceptable workload;

receiving a machine readable command from the location associated with the human transcriber, the machine readable command comprising a representation of an application response to the recorded audio data, the machine readable command created by the human transcriber;

creating an application command based on the machine readable command; and

transmitting the application command to the wireless communication device.

2. The method in claim 1 wherein the number of simultaneous servers running speech recognition software receiving the same audio data is defined by the system administrator.

3. The method in claim 1 including one or more additional servers running speech recognition software;

and

Wherein the recorded audio data is further processed by the one or more additional servers is based on the type of audio data being processed.

4. The method in claim 1 including one or more additional servers running speech recognition software;

and

Wherein the recorded audio data is further processed by the one or more additional servers is based on the communication device user'"'"'s options.

5. A method of using speech recognition software for recorded audio data received from a wireless communication device, comprising:

Receiving recorded audio data communicated from a wireless communication device and directing the audio data to more than one simultaneous servers running speech recognition software, wherein the number of simultaneous servers running speech recognition software receiving the same audio data is controlled by the communication device user'"'"'s options;

Receiving a confidence level of recognition from each server running speech recognition software; and

Routing the recognition result with the highest confidence level for further processing;

wherein directing the audio data to more than one simultaneous servers running speech recognition software includes;

appending at least one unique identifier to the recorded audio data, the unique identifier associated with at least one human transcriber who has previously reviewed voice commands from a user currently associated with the wireless communication device, the unique identifier further indicative of an accent of the user currently associated with the wireless communication device;

wherein receiving a confidence level of recognition from each server running speech recognition software includes;

upon detecting that each confidence level of recognition from each server running speech recognition software is below a predefined level, routing the recorded audio data to a location associated with the human transcriber who has previously reviewed voice commands from a user currently associated with the wireless communication device;

receiving a machine readable command from the location associated with the human transcriber, the machine readable command comprising a representation of an application response to the recorded audio data, the machine readable command created by the human transcriber;

creating an application command based on the machine readable command; and

transmitting the application command to the wireless communication device.

6. A method of using speech recognition software for recorded audio data received from a wireless communication device, comprising:

Receiving recorded audio data communicated from a wireless communication device and directing the audio data to more than one simultaneous servers running speech recognition software, wherein the number of simultaneous servers running speech recognition software receiving the same audio data is controlled by the communication device user'"'"'s options;

Receiving a confidence level of recognition from each server running speech recognition software; and

Routing the recognition result with the highest confidence level for further processing;

wherein receiving a confidence level of recognition from each server running speech recognition software includes;

upon detecting that each confidence level of recognition from each server running speech recognition software is below a predefined level, routing the recorded audio data to a location associated with a human transcriber identified according to criteria defined by a user currently associated with the wireless communication device;

creating data, to be presented at the location associated with the human transcriber, representing indication of the user'"'"'s historical activity;

receiving a machine readable command from the location associated with the human transcriber, the machine readable command comprising a representation of an application response to the recorded audio data, the machine readable command created by the human transcriber;

creating an application command based on the machine readable command;

transmitting the application command to the wireless communication device;

creating a prompt to be presented at the location associated with the human transcriber, the prompt requesting an update to a speech recognition grammar file associated with the user currently associated with the wireless communication device, the update indicative of an interpretation of the recorded audio data made by the human transcriber, the updated speech recognition grammar file enhancing the servers running speech recognition software ability to process subsequent recorded audio data created by the user currently associated with the wireless communication device.

7. A method of using speech recognition software for recorded audio data received from a wireless communication device, comprising:

Receiving recorded audio data communicated from a wireless communication device and directing the audio data to more than one simultaneous servers running speech recognition software, wherein the number of simultaneous servers running speech recognition software receiving the same audio data is controlled by the communication device user'"'"'s options;

Receiving a confidence level of recognition from each server running speech recognition software; and

Routing the recognition result with the highest confidence level for further Processing;

wherein directing the audio data to more than one simultaneous servers running speech recognition software includes;

appending at least one unique identifier to the recorded audio data, the unique identifier associated with a user of the wireless communication device;

wherein receiving a confidence level of recognition from each server running speech recognition software includes;

upon detecting that each confidence level of recognition from each server running speech recognition software is below a predefined level, routing the recorded audio data to a location associated with the human transcriber;

based on the unique identifier, selecting a grammar file, the grammar file including a representation of at least one example of the user'"'"'s speech pattern;

transmitting the grammar file for presentation at the location associated with the human transcriber;

receiving a machine readable command from the location associated with the human transcriber, the machine readable command comprising a representation of an application response to the recorded audio data, the machine readable command created by the human transcriber;

creating an application command based on the machine readable command; and

transmitting the application command to the wireless communication device.

8. A method of using speech recognition software for recorded audio data received from a wireless communication device, comprising:

Receiving recorded audio data communicated from a wireless communication device and directing the audio data to more than one simultaneous servers running speech recognition software, wherein the number of simultaneous servers running speech recognition software receiving the same audio data is controlled by the communication device user'"'"'s options;

Receiving a confidence level of recognition from each server running speech recognition software; and

Routing the recognition result with the highest confidence level for further processing;

wherein receiving a confidence level of recognition from each server running speech recognition software includes;

upon detecting that each confidence level of recognition from each server running speech recognition software is below a predefined level, routing the recorded audio data to a location associated with a human transcriber currently experiencing an acceptable workload, wherein the communication device user'"'"'s options include indicating the user has selected to provide speech structured in accordance with a standardized format for voice commands, the recorded audio data representing speech structured in accordance with the standardized format for voice commands;

receiving a machine readable command from the location associated with the human transcriber, the machine readable command comprising a representation of an application response to the recorded audio data, the machine readable command created by the human transcriber;

creating an application command based on the machine readable command; and

transmitting the application command to the wireless communication device.