Noise recognizer for speech recognition systems

• US 6,324,499 B1
• Filed: 03/08/1999
• Issued: 11/27/2001
• Est. Priority Date: 03/08/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Lewis, James R., Ballard, Barbara
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US09/264,122
• Time in Patent Office: 995 Days
• Field of Search: 704/233, 704/200, 704/246, 704/251, 704/257, 704/235, 704/256, 704/255, 704/226, 704/227, 704/228
• US Class Current: 704/233
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/226 using non-speech characteristics

Abstract

A method and system for responding to randomly occurring noise in a voice recognition application program. The system receives an audio signal representative of sound in an audio environment and processes the audio signal to identify certain non-speech sounds. A pre-defined action is performed in response to the non-speech sound which has been identified. The pre-defined action is selected from the group consisting of disabling a microphone source of the audio signal, suspending further processing of the audio signal by the speech recognition system, executing a user-defined macro, and ignoring the sound. The system may perform additional steps including recording a sound which is to be identified as a non-speech sound and assigning one of the pre-defined actions to be performed in response when the non-speech sound has been identified.

Claims

1. In a speech recognition system, a method for responding to randomly occurring environmental and personal noises, comprising the steps of:

identifying and recording at least one randomly occurring noise selected from the group consisting of environmental and personal noises;

mapping said at least one identified and recorded randomly occurring noise to a pre-defined action; and

,

in response to receiving a randomly occurring noise which has been mapped to a pre-defined action, performing said pre-defined action.

2. The method according to claim 1 wherein said pre-defined action is selected from one of the group consisting of disabling a microphone source of an audio signal, suspending further processing of said audio signal by the speech recognition system, executing a user-defined macro, and ignoring said randomly occurring noise.

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

assigning one of said pre-defined actions to be performed in response when said randomly occurring background noise has been identified.

4. The method according to claim 1 wherein said environmental noise is selected from the group consisting of keyboard noises and a telephone ringer.

5. A system for responding to randomly occurring environmental and personal noises in a speech recognition application, comprising:

audio means for recording an audio signal representative of a randomly occurring noise selected from the group consisting of environmental and personal noises;

mapping means for mapping said recorded randomly occurring noise to a pre-defined action; and

,

system reconfiguration means for performing said pre-defined action in response to receiving a noise which is identified as said randomly occurring noise.

6. The system according to claim 5 wherein said pre-defined action is selected from one of the group consisting of disabling a microphone source of an audio signal, disabling audio sound processing means for processing said audio signal, disabling speech recognition processing performed by the system, executing a user-defined macro, and ignoring the randomly occurring background noise.

7. The system according to claim 6 further comprising means for assigning one of said pre-defined actions to be performed in response when said randomly occurring background noise has been identified.

8. The system according to claim 5 wherein said environmental noise is selected from the group consisting of keyboard noises and a telephone ringer.

9. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

identifying and recording at least one randomly occurring noise selected from the group consisting of environmental and personal noises;

mapping said at least one identified and recorded randomly occurring noise to a pre-defined action; and

,

in response to receiving a randomly occurring noise which has been mapped to a pre-defined action, performing said pre-defined action.

10. The machine readable storage according to claim 9 wherein said pre-defined action is selected from one of the group consisting of disabling a microphone source of an audio signal, suspending further processing of said audio signal by the speech recognition system, executing a user-defined macro, and ignoring said randomly occurring noise.

11. The machine readable storage according to claim 9 comprising the further step of:

assigning one of said pre-defined actions to be performed in response when said randomly occurring background noise has been identified.

12. A method for responding to randomly occurring background noise in a speech recognition system, comprising the steps of:

receiving an audio signal representative of sound in an audio environment;

continuously determining from said audio signal if said audio signal originated as speech or at least one of a randomly occurring noise selected from the group consisting of environmental and personal noises; and

,

executing a pre-defined function mapped to said randomly occurring noise in accordance with said determining step.

13. The method according to claim 12, further comprising the step of executing speech recognition of said audio signal unless said sound is determined to have originated as at least one of said randomly occurring noise selected from the group consisting of environmental and personal noises.

14. The method according to claim 12, further comprising the step of interrupting speech recognition of said audio signal when said sound is determined to have originated as at least one of said randomly occurring noise selected from the group consisting of environmental and personal noises.

15. The method according to claim 14, further comprising the step of executing a user-defined macro after said interrupting step.

16. The method according to claim 12, wherein said predefined function is to ignore said audio signal if it is determined to have originated as at least one of said randomly occurring noise selected from the group consisting of environmental and personal noises.

17. The method of claim 12, comprising the step of executing at least one of a plurality of pre-defined functions in accordance with said determining step.

18. The method of claim 12, further comprising the steps of:

recording randomly occurring noises selected from the group consisting of environmental and personal noises;

associating a respective pre-defined function with each recorded randomly occurring noise; and

,

upon detection of any one of said at least one of said randomly occurring noises by said determining step, automatically executing said respective pre-defined function associated with said detected randomly occurring noise.