Voice control system with multiple voice recognition engines

• US 20020091518A1
• Filed: 12/07/2001
• Published: 07/11/2002
• Est. Priority Date: 12/07/2000
• Status: Active Grant

• Current Assignee: ART Advanced Recognition Technologies Ltd (Microsoft Corporation)
• Original Assignee: ART Advanced Recognition Technologies Ltd (Microsoft Corporation)
• Inventors: Yadid, Tal, Ben-Dor, Nir, Baruch, Amit, Riemer, Itay, Mochary, Ran
• Granted Patent: US 7,203,651 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

Described is a control unit including a recognition result receiver able to receive a recognition result, a recognition result association unit having associations of results with recognition engines, and a recognition engine activator able to activate the recognition engine associated with the recognition result. Also described is a device including a microphone, an analog to digital converter able to convert input received by the microphone, a first speech recognition engine adapted to perform a first type of recognition on an output of the analog to digital converter, and a second recognition engine adapted to perform a second type of recognition on the output.

Claims

1. A control unit comprising:

a recognition result receiver able to receive a recognition result;

a recognition result association unit having associations of results with recognition engines; and

a recognition engine activator able to activate the recognition engine associated with said recognition result.

2. A control unit according to claim 1 and further comprising a device communicator able to send feedback commands to a device.

3. A control unit according to claim 2 wherein said device is selected from the group consisting of a telephone, a computer, a car accessory, a lock a PDA, an audio device, a video device, and a voice controlled appliance.

4. A device comprising:

a microphone;

an analog to digital converter able to convert input received by said microphone;

a first speech recognition engine adapted to perform a first type of recognition on an output of said analog to digital converter; and

a second recognition engine adapted to perform a second type of recognition on said output.

5. A device according to claim 4 and further comprising a vocoder.

6. A device according to claim 4 wherein said type of recognition and said second type of recognition are selected from the group consisting of:

a speaker independent commands and control engine;

a speaker independent name dialing engine;

a speaker dependent name dialing engine;

a speaker independent digit dialing multilanguage engine; and

a speaker dependent digit dialing language independent engine.

7. A voice controlled apparatus comprising:

at least two speech recognition engines; and

a control unit able to switch between said engines based on recognition results of said engines.

8. A voice controlled apparatus according to claim 7 and after comprising a vocoder.

9. A voice controlled apparatus according to claim 7 wherein said at least two speech recognition engines are selected from the group consisting of:

a speaker independent commands and control engine;

a speaker independent name dialing engine;

a speaker dependent name dialing engine;

a speaker independent digit dialing multilanguage engine; and

a speaker dependent digit dialing language independent engine.

10. A voice controlled apparatus according to claim 7 and further comprising a user feedback unit.

11. A voice controlled apparatus according to claim 10 wherein said user feedback unit is selected from the group consisting of a speaker and a display unit.

13. A method according to claim 12 and further comprising sending feedback to a user.

15. A method according to claim 14 and further comprising activating a recognition engine.

12. A method comprising:

recognizing a first audio input by a first recognition engine;

activating a second recognition engine previously associated with said recognized input; and

recognizing a second audio input by said second recognition engine.

14. A method comprising:

a recognizing an audio input by a first recognition engine;

recognizing said audio input by a second recognition engine; and

choosing between a first recognized result of said first engine and a second recognized result of said second engine.

16. A device comprising:

a microphone;

an analog to digital converter able to convert input received by said microphone;

a first speech recognition engine adapted to perform a first type of recognition on an output of said analog to digital converter;

a second recognition engine adapted to perform a second type of recognition on said output; and

a speaker able to provide audio feedback related to at least one recognition result from said first and said second recognition engines.

17. A voice controlled telephone comprising:

a recognition result receiver able to receive a recognition result;

a recognition result association unit having associations of results with recognition engines;

a recognition engine activator able to activate the recognition engine associated with said recognition result; and

a speaker able to provide audio feedback related to said recognition result.

18. A voice controlled telephone comprising:

a microphone able to receive voice input;

an analog to digital converter able to convert said input;

at least two speech recognition engines able to perform recognition on an output of said analog to digital converter; and

a control unit able to switch between modes of operation based all said output.

19. A voice controlled telephone comprising:

a recognition result receiver able to receive a recognition result;

a recognition result association unit having associations of results with recognition engines; and

a recognition engine activator able to activate the recognition engine associated with said recognition result.