Speech recognition apparatus having multiple audio inputs to cancel background noise from input speech

• US 7,050,971 B1
• Filed: 09/20/2000
• Issued: 05/23/2006
• Est. Priority Date: 09/23/1999
• Status: Expired due to Term

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Kaufholz, Paul A. P.
• Primary Examiner(s): Storm, Donald L.
• Application Number:
  US09/666,398
• Time in Patent Office: 2,071 Days
• Field of Search: 704/226, 704/227, 704/228, 381/71.3
• US Class Current: 704/226
• CPC Class Codes: G10L 21/0364 for improving intelligibility

Abstract

A speech recognition apparatus including an audio cancellation module is disclosed. The module includes an audio input for receiving an audio signal from a microphone. The module also includes at least two audio inputs for receiving audio signals from respective independent audio sources. The audio cancellation module produces a speech signal by canceling two of the independent audio source signals from the microphone signal. A speech recognizer is used to recognize at least part of the speech signal.

Claims

1. A speech recognition apparatus comprising:

an audio cancellation module, including;

an audio input for receiving an audio signal that includes a speech signal and a plurality of different background noises;

at least two additional audio inputs for receiving at least two audio source signals, respectively, from independent audio sources that primarily do not include said speech signal, the at least two audio source signals contributing to the plurality of different background noises of the audio signal and are within a proximity of the sensitivity range of a microphone for capturing said speech signal and each respective audio input arranged within a proximity of a respective audio source,

wherein the audio cancellation module is operative to cancel the at least two audio source signals from the audio signal received, substantially sequential, to leave a remainder of the audio signal received that comprises primarily the speech signal; and

a speech recognizer for recognizing at least part of the speech signal.

2. A speech recognition apparatus as claimed in claim 1, further comprising:

a controller for issuing at least one command message to a further apparatus via a control communication network in response to a spoken instruction from a user that is recognized by the speech recognizer.

3. A speech recognition apparatus as claimed in claim 2, wherein the controller is operative to issue the at least one command message according to remote control messages associated with the further apparatus.

4. A speech recognition apparatus as claimed in claim 1, wherein at least one of the two audio source signals is received via an audio communication network from an audio source unit that is external to the speech recognition apparatus.

5. A speech recognition apparatus as claimed in claim 1, wherein the speech recognition apparatus includes at least one audio input for receiving an external audio source signal from an audio source unit that is external to the speech recognition apparatus;

the audio source signal from the audio source unit that is external to the speech recognition apparatus being received substantially for the purpose of canceling the external audio source signal from the audio signal.

6. A consumer electronics system comprising:

at least two independent audio source apparatuses;

an audio cancellation module, including;

an audio input for receiving an audio signal that includes a speech signal and a plurality of different background noises; and

at least two additional audio inputs for receiving, respectively, independent audio source signals from respective ones of the audio source apparatuses, the at least two independent audio source signals contributing to the audio signal;

the audio cancellation module being operative to cancel the at least two independent audio source signals from the audio signal received, substantially sequential, to leave a remainder of the audio signal received that comprises primarily the speech signal; and

a speech recognizer for recognizing at least part of the speech signal that remains.

7. A system as claimed in claim 6, further comprising a control unit for, in response to a spoken instruction from a user that is recognized by the speech recognizer, issuing at least one command message to an apparatus in the system via a communication network.

8. A system as claimed in claim 7, wherein at least one of the independent audio source signals is received via the communication network from the associated audio source apparatus.

9. A system as claimed in claim 8, wherein the audio cancellation module is located in an apparatus of the system, where the apparatus includes at least one audio input for receiving an audio source signal from an audio source apparatus external to the apparatus;

the audio signal being received substantially for the purpose of canceling this audio signal from the audio signal.

10. An audio cancellation module, comprising:

an audio input for receiving an audio signal that includes a speech signal and a plurality of different background noises, said audio signal including an indication of a highest signal source from among said speech signal and each of said plurality of different background noises; and

at least two additional audio inputs for receiving audio source signals, respectively, from respective independent audio sources, the at least two audio source signals contributing to the plurality of different background noises included in the received audio signal;

the audio cancellation module being operative to produce a signal by canceling from the audio signal received those signals not indicated to be the highest signal source.