Model-based voice activity detection system and method using a log-likelihood ratio and pitch

Patent 6615170 Issued on September 2, 2003. Estimated Expiration Date:

March 7, 2020. Estimated Expiration Date is calculated based on simple USPTO term provisions. It does not account for terminal disclaimers, term adjustments, failure to pay maintenance fees, or other factors which might affect the term of a patent.

Abstract Claims Description Full Text

Patent References

Process and device for creating comfort noise in a digital speech transmission system
Patent #: 5812965
Issued on: 09/22/1998
Inventor: Massaloux

Line spectral frequencies and energy features in a robust signal recognition system
Patent #: 6009391
Issued on: 12/28/1999
Inventor: Asghar, et al.

Matrix quantization with vector quantization error compensation for robust speech recognition
Patent #: 6070136
Issued on: 05/30/2000
Inventor: Cong, et al.

Quantization using frequency and mean compensated frequency input data for robust speech recognition
Patent #: 6219642
Issued on: 04/17/2001
Inventor: Asghar, et al.

Speech codec employing noise classification for noise compensation
Patent #: 6240386
Issued on: 05/29/2001
Inventor: Thyssen, et al.

Soft decision signal estimation
Patent #: 6349278
Issued on: 02/19/2002
Inventor: Krasny, et al.

Adaptive filter featuring spectral gain smoothing and variable noise multiplier for noise reduction, and method therefor Patent #: 6351731
Issued on: 02/26/2002
Inventor: Anderson, et al.

Inventors

Application

No. 09/519960 filed on 03/07/2000

US Classes:

704/233, Detect speech in noise704/231Recognition

Examiners

Primary: To, Doris H.
Assistant: Opsasnick, Michael N.

Attorney, Agent or Firm

F. Chau & Associates, LLP

International Classes

G10L 11/02 (20060101)
G10L 11/00 (20060101)

Abstract

A system and method for voice activity detection, in accordance with the invention includes the steps of inputting data including frames of speech and noise, and deciding if the frames of the input data include speech or noise by employing a log-likelihood ratio test statistic and pitch. The frames of the input data are tagged based on the log-likelihood ratio test statistic and pitch characteristics of the input data as being most likely noise or most likely speech. The tags are counted in a plurality of frames to determine if the input data is speech or noise.

Other References

Steven F. Boll, "Suppression of Acoustic Noise in Speech Using Spectral Subtraction," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-27, No. 2, pp. 113-120, Apr. 1979
Rabiner et al., "Application of an LPC Distance Measure to the Voiced-Unvoiced-Silence Detection Problem," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-25, No. 4, pp. 338-343, Aug. 1977
Rangoussi et al., "Higher Order Statistics Based Gaussianity Test Applied to On-Line Speech Processing," In Proc. of the IEEE Asilomar Conf., pp. 303-807, 1995
El-Maleh et al., "Comparison of Voice Activity Detection Algorithms for Wireless Personal Communications Systems," Proc. IEEE Canadian Conference on Electrical and Computer Engineering (ST. John s, Nfld.), pp. 470-473, May 1997
Bahl et al., "Performance of the IBM Large Vocabulary Continuous Speech Recognition System on the ARPA Wall Street Journal Task"