Single channel sound separation

Details Single channel sound separation Single channel sound separation

2007-07-10

2007-07-10

Hudspeth, David (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

C704S270000, C704S233000

Reexamination Certificate

active

10406802

ABSTRACT:
The speech of two or more simultaneous speakers (or other simultaneous sounds) conveyed in a single channel are distinguished. Joint acoustic/modulation frequency analysis and display tools are used to localize and separate sonorant portions of multiple-speakers' speech into distinct regions using invertible transform functions. For example, the regions representing one of the speakers are set to zero, and the inverted modified display maintains only the speech of the other speaker. A combined audio signal is manipulated using a base acoustic transform, followed by a second modulation transform, which separates the combined signals into distinguishable components. The components corresponding to the undesired speaker are masked, leaving only the second modulation transform of the desired speaker's audio signal. An inverse second modulation transform of the desired signal is performed, followed by an inverse base acoustic transform of the desired signal, providing an audio signal for only the desired speaker.

REFERENCES:
patent: 6321200 (2001-11-01), Casey
patent: 6430528 (2002-08-01), Jourjine et al.
patent: 6910013 (2005-06-01), Allegro et al.
patent: 7076433 (2006-07-01), Ito et al.
patent: 2002/0176353 (2002-11-01), Atlas et al.
Vinton et al., “Scalable and progressive audio codec”, IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001, pp. 3277-3280, vol. 5.
Greenberg et al., “The modulation spectrogram: in pursuit of an invariant representation of speech”, International Conference on Acoustics, Speech, and Signal Processing, 1997, pp. 1647-1650, vol. 3.
Amari, Shun-Ichi and Andrzej Cichocki. 1998. “Adaptive Blind Signal Processing—Neural Network Approaches.”Proceedings of the IEEE:86 (October): 2026-48.
Bregman, Albert S. 1990.Auditory Scene Analysis: The Perceptual Organization of Sound.The MIT Press.
Beauvois, Michael W. and Ray Meddis. 1991. “A Computer Model of Auditory Stream Segregation.”The Quarterly Journal of Experimental Psychology: 43A(3):517-41.
Cardoso, Jean-Francois. 1998. “Blind Signal Separation: Statistical Principles.”Proceedings of the IEEE:86 (October):2009-25.
Choi, Seungjin and Andrzej Cichocki. n.d. Adaptive Blind Separation of Speech Signals: Cocktail Party Problem. Frontier Research Program, RIKEN, Saitama, Japan: 6pp.
Girolami, M. n.d. Noise Reduction and Speech Enhancement via Temporal Anti-Hebbian Learning. University of Paisley, Scotland:4pp.
Koutras, Athanasios, Evangelos Dermatas, and George Kokkinakis. Recognizing Simultaneous Speech: A Genetic Algorithm Approach. University of Patras, Hellas, Cyprus. 4pp.
Lee, Te-Won, Anthony J. Bell, Russell H. Lambert. n.d. Blind separation of delayed and convolved sources. 7pp.
MacDougall-Shackleton, Scott A., Stewart H. Hulse, Timothy Q. Gentner, and Wesley White. 1998. Auditory scene analysis by European starlings (Sturnus vulgaris): Perceptual segregation of tone sequences.J. Acoust. Soc. Am.: 103(6)(June):3581:87.
Meyer, G.F., F. Plante, and F. Berthommier. 1997. “Segregation of Concurrent Speech with the Reassigned Spectrum.”IEEE:1203-06.
Parsons, Thomas W. 1976. “Separation of speech from interfering speech by means of harmonic selection.”J. Acoust. Soc. Am.:60/4(October):911-18.
Westner, Alex and V. Michael Bove, Jr. n.d. Applying Blind Source Separation and Deconvolution to Real-World Acoustic Environments. MIT Media Lab:10pp.
Yen, Kuan-Chieh, Jun Huang, Yunxin Zhao. n.d. Co-Channel Speech Separation in the Presence of Correlated and Uncorrelated Noises. University of Illinois Urbana-Champaign. 4pp.
Yen, Kuan-Chieh and Yunxin Zhao. n.d. Co-Channel Speech Separation for Robust Automatic Speech Recognition: Stability and Efficiency. University of Illinois Urbana-Champaign. 4pp.

Affiliated with

Also associated with

Rating

Single channel sound separation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Single channel sound separation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Single channel sound separation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3720609