Selective noise/channel/coding models and recognizers for automatic speech recognition

• US 5,970,446 A
• Filed: 11/25/1997
• Issued: 10/19/1999
• Est. Priority Date: 11/25/1997
• Status: Expired

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Goldberg, Randy G., Rosen, Kenneth H., Sachs, Richard M., Winthrop, III, Joel A.
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/978,527
• Time in Patent Office: 693 Days
• Field of Search: 704/233, 704/231, 704/256, 704/255, 704/226, 704/227, 704/228, 704/270
• US Class Current: 704/233
• 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

Abstract

An apparatus and method for the robust recognition of speech during a call in a noisy environment is presented. Specific background noise models are created to model various background noises which may interfere in the error free recognition of speech. These background noise models are then used to determine which noise characteristics a particular call has. Once a determination has been made of the background noise in any given call, speech recognition is carried out using the appropriate background noise model.

Claims

1. A method for the robust recognition of speech in a noisy environment, comprising the steps of:

receiving the speech;

recording an amount of data related to the noisy environment;

analyzing the recorded data;

selecting at least one appropriate background noise model on the basis of the recorded data; and

performing speech recognition with the at least one selected background noise model.

2. The method according to claim 1, further comprising the step of:

modeling at least one background noise in a noisy environment to create at least one background noise model.

3. The method according to claim 1, further comprising the step of:

determining the correctness of the at least one selected background noise model, wherein if the at least one selected model is determined to be incorrect, loading at least one other background noise model for use in the step of performing speech recognition.

4. The method according to claim 1, further comprising the step of:

constructing a background noise database for use in analyzing the recorded data on the noisy environment.

5. The method according to claim 4, wherein the background noise database is dynamically updated for each location from which data is recorded.

6. The method according to claim 1, wherein the step of analyzing the recorded data is accomplished by using at least one of a plurality of signal information.

7. The method according to claim 1, wherein the step of analyzing the recorded data is accomplished by using a correct match percentage for a plurality of background noise models determined by an input response.

8. The method according to claim 1, wherein the step of performing speech recognition is accomplished by at least one recognizer.

9. A method for improving recognition of speech subjected to noise, the method comprising the steps of:

sampling a connection noise;

searching a database for a noise model most closely matching the sampled connection noise; and

applying the most closely matching noise model to a speech recognition process.

10. The method according to claim 9, wherein the connection noise includes at least one of city noise, motor vehicle noise, truck noise, traffic noise, airport noise, subway train noise, cellular interference noise, channel condition noise, telephone microphone characteristics noise, cellular coding noise, and Internet connection noise.

11. The method according to claim 9, wherein the noise model is constructed by modeling at least one connection noise.

12. The method according to claim 9, wherein when a speech recognition error rate is determined to be above a predetermined level, the system substitutes the applied noise model by applying at least one other noise model.

13. The method according to claim 9, wherein at least one speech recognition unit is used.