Microphone initialization enhancement for speech recognition

• US 7,636,661 B2
• Filed: 06/30/2005
• Issued: 12/22/2009
• Est. Priority Date: 07/01/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: De Leeuw, Adam Pieter, Groeger, Steven, Hayton, Stuart John
• Primary Examiner(s): Han; Qi
• Application Number:
  US11/172,045
• Publication Number:
  US 20060004573A1
• Time in Patent Office: 1,636 Days
• Field of Search: 704/251, 704/247, 704/254, 704/231
• US Class Current: 704/251
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal

Abstract

A method and arrangement for improved speech recognition in a telephonically challenging speakerphone in-car environment. The method includes receiving a signal from a microphone representative of speech to be recognized, performing detection of a transition in the signal indicative of switch on of the microphone, and, in response to the detection, performing speech recognition on the signal with reduced contribution from an initial portion thereof. The initial portion may be treated as optional speech, the speech recognition may be performed with a predetermined redundant sound, and a user may be requested to speak the predetermined redundant sound when speech recognition has fallen below a predetermined threshold. Thus, recognition may be made possible when otherwise it would not be possible, recognition match scoring will be increased as the low weighting given by deleted initial sounds will be eliminated and therefore confusion of the recognized phrase will be reduced.

Claims

1. A method of speech recognition for use with a system having a microphone, comprising:

receiving a signal from the microphone representative of a speech to be recognized, wherein the microphone was turned off before receiving the signal;

identifying an initial portion of the speech that contains omitted sounds;

performing speech recognition on the signal with reduced contribution from the initial portion of the speech, wherein a quantity by which the contribution of the initial portion is reduced is a configurable parameter;

when speech recognition has fallen below a predetermined threshold, requesting a user to speak a predetermined redundant word before an intended speech, wherein the predetermined redundant word turns on the microphone and is user configurable; and

speech recognizing the intended speech after the predetermined redundant word.

2. The method of claim 1, wherein the initial portion comprises at least one of a first word and a received and terminal portion of the first word of a spoken series of words contained within the signal.

3. The method of claim 2, further comprising the step of:

establishing an utterance initiating word, wherein the first word is the utterance initiating word.

4. The method of claim 1, wherein the system is a telephone speaker phone system.

5. The method of claim 4, wherein the system is an in-car system.

6. A speech recognition arrangement for use with a system having a microphone, comprising:

means for receiving a signal from the microphone representative of a speech to be recognized, wherein the microphone was turned off before receiving the signal;

means for identifying an initial portion of the speech that contains omitted sounds;

means for performing speech recognition on the signal with reduced contribution from the initial portion of the speech, wherein a quantity by which the contribution of the initial portion is reduced is a configurable parameter;

means for, when speech recognition has fallen below a predetermined threshold, requesting a user to speak a predetermined redundant word before an intended speech, wherein the predetermined redundant word turns on the microphone and is user configurable; and

means for speech recognizing the intended speech after the predetermined redundant word.

7. The arrangement of claim 6, wherein the initial portion comprises at least one of a first word and a received and terminal portion of the first word of a spoken series of words contained within the signal.

8. The arrangement of claim 7, further comprising:

means for establishing an utterance initiating word, wherein the first word is the utterance initiating word.

9. The arrangement of claim 6, wherein the system is a telephone speaker phone system.

10. The arrangement of claim 9, wherein the system is an in-car system.