SPEECH ENHANCEMENT

• US 20150255083A1
• Filed: 10/30/2012
• Published: 09/10/2015
• Est. Priority Date: 10/30/2012
• Status: Active Grant

• Current Assignee: Cerence Inc., Cerence Operating Company (Cerence Inc.)
• Original Assignee: Naunce Communication Incorporated
• Inventors: Krini, Mohamed, Schalk-Schupp, Ingo, Hannon, Patrick
• Granted Patent: US 9,613,633 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• 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 19/04 using predictive techniques
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

A speech signal processing system is described for use with automatic speech recognition and hands free speech communication. A signal pre-processor module transforms an input microphone signal into corresponding speech component signals. A noise suppression module applies noise reduction to the speech component signals to generate noise reduced speech component signals. A speech reconstruction module produces corresponding synthesized speech component signals for distorted speech component signals. A signal combination block adaptively combines the noise reduced speech component signals and the synthesized speech component signals based on signal to noise conditions to generate enhanced speech component signals for automatic speech recognition and hands free speech communication.

Claims

1. A computer-implemented method employing at least one hardware implemented computer processor for speech signal processing, the method comprising:

transforming an input microphone signal into corresponding speech component signals;

applying noise reduction to the speech component signals to generate noise reduced speech component signals;

producing corresponding synthesized speech component signals for distorted speech component signals; and

adaptively combining the noise reduced speech component signals and the synthesized speech component signals based on signal to noise conditions and extracted features from the input to generate an enhanced speech component signals for automatic speech recognition and hands free speech communication.

2. The method according to claim 1, wherein the speech component signals are time domain speech component signals.

3. The method according to claim 1, wherein the speech component signals are frequency domain speech component signals.

4. The method according to claim 1, wherein a non-linear function of speech components is used for producing the synthesized speech component signals.

5. The method according to claim 4, wherein the non-linear function operates to restore distorted or missing harmonics of the distorted speech component signals.

6. The method according to claim 1, wherein relevant features extracted from the distorted speech component signals are used for producing the synthesized speech component signals.

7. The method according to claim 1, wherein a source-filter model is used for producing the synthesized speech component signals.

8. The method according to claim 1, wherein a parametric model of envelope shape is used for producing the synthesized speech component signals.

9. The method according to claim 1, wherein producing corresponding synthesized speech component signals includes noise suppression pre-processing of the distorted speech component signals to provide speech synthesis reference signals.

10. The method according to claim 1, wherein producing corresponding synthesized speech component signals includes dividing the distorted speech component signals into different frequency bands.

11. A speech signal processing system employing at least one hardware implemented computer processor, the system comprising:

a signal pre-processor for transforming an input microphone signal into corresponding speech component signals;

a noise suppression module for applying noise reduction to the speech component signals to generate noise reduced speech component signals;

a speech reconstruction module for producing corresponding synthesized speech component signals for distorted speech component signals; and

a signal combination block for adaptively combining the noise reduced speech component signals and the synthesized speech component signals based on signal to noise conditions to generate enhanced speech component signals for automatic speech recognition and hands free speech communication.

12. The system according to claim 11, wherein the speech component signals are time domain speech component signals.

13. The system according to claim 11, wherein the speech component signals are frequency domain speech component signals.

14. The system according to claim 11, wherein the speech reconstruction module uses a non-linear function of speech components for producing the synthesized speech component signals.

15. The system according to claim 14, wherein the non-linear function operates to restore distorted or missing harmonics of the distorted speech component signals.

16. The system according to claim 11, wherein the speech reconstruction module uses relevant features extracted from the distorted speech component signals for producing the synthesized speech component signals.

17. The system according to claim 11, wherein the speech reconstruction module uses a source-filter model for producing the synthesized speech component signals.

18. The system according to claim 11, wherein the speech reconstruction module uses a parametric model of envelope shape for producing the synthesized speech component signals.

19. The system according to claim 11, wherein the speech reconstruction module includes a noise pre-processing module for noise suppression of the distorted speech component signals to provide speech synthesis reference signals.

20. The system according to claim 11, wherein the speech reconstruction module divides the distorted speech component signals into different frequency bands.