Memories Consortium

A Sixth Framework Programme

Established June 2006, under the: Information Society Technologies

Target: Design for an audio semantic indexation system, allowing information retrieval for the access to archive content

Researcher: Prof. Israel cohen

Subject:Single Sensor Source Separation

Memories Management Meeting, Haifa , 18-19/11/07

From ICT Results

Faster, easier way to access audiovisual assets

Millions of hours of old shows sit collecting dust in the basements of TV and radio broadcasters. Digging through these audiovisual treasure troves is becoming faster and easier thanks to software developed by European researchers.

 

Students:

Ari Abramson, Ph.D. Student (direct track) Markov-Switching GARCH Models and Applications to Digital Speech Processing
Yekutiel Avargel, Ph.D. Student (direct track) System Identification and Adaptive Filtering in the Short-Time Fourier Transform Domain.
Yevgeni Litvin, M.Sc. Student Single-Channel Blind Source Separation of Audio Signals

A related graduate course is given by Prof. Israel Cohen
“Digital Speech Processing in NoisyEnvironments” (049035)

Students Presentations from this course (2006-2007)

Subject Reference Presented by
Time Difference of Arrival Estimation of Speech Source in a Noisy and Reverberant Environment TG Dvorkind, S Gannot Signal Processing, vol. 85, 2005 Ronen Talmon (2007)
Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria T Virtanen IEEE Transaction on Audio, Speech and Language Processing, 2006 – ieeexplore.ieee.org Alexander Berkovich (2007)
A Bayesian Approach for Blind Separation of Sparse Sources C Févotte, SJ Godsill IEEE Transaction on Audio, Speech and Language Processing, 2006 – ieeexplore.ieee.org Ofir Mebel (2007)
Audio Source Separation With a Single Sensor L Benaroya, F Bimbot, R Gribonval IEEE Transaction on Audio, Speech and Language Processing, 2006 – ieeexplore.ieee.org Itai Ram (2007)
Separation of Singing Voice from Music Accompaniment for Monaural Recordings Y Li, D Wang IEEE Transaction on Audio, Speech and Language Processing, 2007 – ieeexplore.ieee.org Assaf Solomovitch (2007)
On Microphone-Array Beamforming From a MIMO Acoustic Signal Processing Perspective J Benesty, J Chen, YA Huang, J Dmochowski IEEE Transaction on Audio, Speech and Language Processing, 2007 – ieeexplore.ieee.org Osnat Goren (2007)
Representation and identification of Systems in the Wavelet Transform Domain Y Avargel, I Cohen Proc. 16th IASTED International Conference on Applied Simulation and Modelling, ASM-2007 Erez Cohen (2007)
Harmonicity-Based Blind Dereverberation for Single-Channel Speech Signals T Nakatani, K Kinoshita, M Miyoshi IEEE Transaction on Audio, Speech and Language Processing, 2007 – ieeexplore.ieee.org Marina Alterman (2007)
Single Channel Nonstationary Stochastic Signal Separation Using Linear Time-Varying Filters JR Hopgood, PJW Rayner IEEE Transaction on Signal Processing, 2003 – ieeexplore.ieee.org Anastasia Dubrovina (2007)
Musical Source Separation Using Time-Frequency Source Priors E Vincent IEEE Transactions on Audio, Speech and Language Processing, 2006 – ieeexplore.ieee.org Adam Cohen(2006)
Single Channel Nonstationary Stochastic Signal Separation Using Linear Time-Varying Filters JR Hopgood, PJW Rayner IEEE Transactions on Acoustics, Speech, and Signal Processing, 2003 – ieeexplore.ieee.org Evgeny (JB) Braginskiy (2006)
Blind Separation of Speech Mixtures via Time-Frequency Masking O Yilmaz, S Rickard IEEE Transactions on Signal Processing [see also Acoustics, Speech, and Signal Processing], 2004 – ieeexplore.ieee.org Dmitry Minkin (2006)
Monaural Speech Segregation Based on Pitch Tracking and Amplitude Modulation G Hu, DL Wang IEEE Transactions on Neural Networks, 2004 – ieeexplore.ieee.org Eli Yazovitsky (2006)
Audio Source Separation With a Single Sensor [1] L. Benaroya, F. Bimbot, R. Gribonval, “Audio source separation with a single sensor, in IEEE Trans. Audio, Speech and Language Processing, vol. 14, no. 1, pp. 191–199, January 2006.
[2] S. Srinivasan, J. Samuelsson, W. B. Kleijn, “Codebook driven short-term predictor parameter estimation for speech enhancement,” in IEEE Trans. Audio, Speech and Language Processing,  vol.14, no. 1, pp. 163-176, January 2006.
Guy Rapaport (2006)
Source Separation with HMM/GMM Using A Single Sensor L Benaroya, F Bimbot Proc. ICA, 2003 – kecl.ntt.co.jpp Yaakov Bucris

(2006)

Microphone Singing Voice Separation Using Source-Adapted Modules A Ozerov, P Philippe, R Gribonval, F Bimbor Applications of Signal Processing to Audio and Acoustics, 2005 – ieeexplore.ieee.org Orly Kohn Feldman

(2006)

A Blind Channel Identification-Based Two Stage Approach to Separation and De-Reverberation of Speech Signals in a Reverberant Environment Y. Huang, J. Benesty, J. Chen IEEE Transactions on Speech and Audio Processing, Vol. 13, no. 5, September 2005 Roee Diamant

(2006)

A Maximum Likelihood Approach to Single-Channel Source Separation GJ Jang, TW Lee Journal of Machine Learning Research, 2003 – MIT Press Tigran Dobin

(2006)

Single Sensor Blind Source Separation of Audio Signals [1] L. Benaroya, F. Bimbot, R. Gribonval, “Audio source separation with a single sensor, in IEEE Trans. Audio, Speech and Language Processing, vol. 14, no. 1, pp. 191–199, January 2006.
[2] S. Srinivasan, J. Samuelsson, W. B. Kleijn, “Codebook driven short-term predictor parameter estimation for speech enhancement,” in IEEE Trans. Audio, Speech and Language Processing,  vol.14, no. 1, pp. 163-176, January 2006.
Guy Rapaport

(2006)

 

SIPL Undergraduates  Projects:

Single Sensor Blind Source Separation of Audio Signals
Students:       Levy Michal , Gedalyahu Kfir
Supervisor:     Guy Rapaport

Separating a Singer from a Band
Students:       Vilenski Yulia, Zon Victoria
Supervisor:     Guy Rapaport

Separating Speech from a Noisy Environment
Students:       Ruben Hanhart, Nadav Malke
Supervisor:     Guy Rapaport

Audio Segmentation and Classification
Students:      Alex Kucherov, Yulia Rabinsky
Supervisor:    Ronen Talmon

Emotional State Recognition in Speech
Students:      Shahar Katz, Adi Manos
Supervisor:    Ronen Talmon

Papers

  1. Abramson and I. Cohen
    Single-Sensor Blind Source Separation Using Classification and Estimation Approach and GARCH Modeling
    IEEE Trans. Audio, Speech and Language Processing, Vol. 16, Issue 8, Nov. 2008, pp. 1528-1540.
  2. Litvin and I. Cohen
    Single-Channel Source Separation of Audio Signals Using Bark Scale Wavelet Packet Decomposition
    Proc. 9th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2009, Grenoble, France, September 1-4 2009, pp. 1-4.
  3. Blouet, G. Rapaport, I. Cohen and C. Fevotte
    Evaluation of Several Strategies for Single Sensor Speech/Music Separation
    Proc. 33rd IEEE Internat. Conf. Acoust. Speech Signal Process., ICASSP-2008, Las Vegas, Nevada, March 30 – April 4, 2008, pp. 37-40.
  4. Abramson and I. Cohen
    Enhancement of Speech Signals Under Multiple Hypotheses Using an Indicator for Transient Noise Presence
    Proc. 32nd IEEE Internat. Conf. Acoust. Speech Signal Process., ICASSP-2007, Honolulu, Hawaii, 15-20 April 2007, pp. IV-553-556. (Best student paper finalist).
  5. Benaroya, R. Blouet, C. Fevotte and I. Cohen
    Single Sensor Source Separation Using Multiple-Window STFT Representation
    Proc. 10th International Workshop on Acoustic Echo and Noise Control, IWAENC-2006, Paris, France, 12-14 September 2006, paper no. 52, pp. 1-4.
  6. Abramson and I. Cohen
    Simultaneous Detection and Estimation Approach for Speech Enhancement and Interference Suppression
    in I. Cohen, J. Benesty and S. Gannot (Eds.), Speech Processing in Modern Communication: Challenges and Perspectives, Springer, 2010, Ch. 5, pp. 127-150.
  7. Blouet and I. Cohen
    Codebook Approaches for Single Sensor Speech/Music Separation
    in I. Cohen, J. Benesty and S. Gannot (Eds.), Speech Processing in Modern Communication: Challenges and Perspectives, Springer, 2010, Ch. 7, pp. 183-198.

Yekutiel Avargel, Ph.D., direct track (2008)
System Identification and Adaptive Filtering in the Short-Time Fourier Transform Domain.
Thesis, Presentation

Ari Abramson, Ph.D., direct track (2008)
Markov-Switching GARCH Models and Applications to Digital Speech Processing.
Thesis, Presentation

Yevgeni Litvin, M.Sc. Student
Single-Channel Blind Source Separation of Audio Signals.
Co-supervisor – Dr. Dan Chazan.