- Research Article
- Open Access
A Maximum Likelihood Estimation of Vocal-Tract-Related Filter Characteristics for Single Channel Speech Separation
EURASIP Journal on Audio, Speech, and Music Processing volume 2007, Article number: 084186 (2006)
We present a new technique for separating two speech signals from a single recording. The proposed method bridges the gap between underdetermined blind source separation techniques and those techniques that model the human auditory system, that is, computational auditory scene analysis (CASA). For this purpose, we decompose the speech signal into the excitation signal and the vocal-tract-related filter and then estimate the components from the mixed speech using a hybrid model. We first express the probability density function (PDF) of the mixed speech's log spectral vectors in terms of the PDFs of the underlying speech signal's vocal-tract-related filters. Then, the mean vectors of PDFs of the vocal-tract-related filters are obtained using a maximum likelihood estimator given the mixed signal. Finally, the estimated vocal-tract-related filters along with the extracted fundamental frequencies are used to reconstruct estimates of the individual speech signals. The proposed technique effectively adds vocal-tract-related filter characteristics as a new cue to CASA models using a new grouping technique based on an underdetermined blind source separation. We compare our model with both an underdetermined blind source separation and a CASA method. The experimental results show that our model outperforms both techniques in terms of SNR improvement and the percentage of crosstalk suppression.
Jutten C, Herault J: Blind separation of sources, part I. An adaptive algorithm based on neuromimetic architecture. Signal Processing 1991,24(1):1-10. 10.1016/0165-1684(91)90079-X
Comon P: Independent component analysis. A new concept? Signal Processing 1994,36(3):287-314. 10.1016/0165-1684(94)90029-9
Bell AJ, Sejnowski TJ: An information-maximization approach to blind separation and blind deconvolution. Neural Computation 1995,7(6):1129-1159. 10.1162/neco.19220.127.116.119
Amari S-I, Cardoso J-F: Blind source separation-semiparametric statistical approach. IEEE Transactions on Signal Processing 1997,45(11):2692-2700. 10.1109/78.650095
Bregman AS: Auditory Scene Analysis. MIT Press, Cambridge, Mass, USA; 1994.
Brown GJ, Cooke M: Computational auditory scene analysis. Computer Speech and Language 1994,8(4):297-336. 10.1006/csla.1994.1016
Cooke M, Ellis DPW: The auditory organization of speech and other sources in listeners and computational models. Speech Communication 2001,35(3-4):141-177. 10.1016/S0167-6393(00)00078-9
Ellis DPW: Using knowledge to organize sound: the prediction-driven approach to computational auditory scene analysis and its application to speech/nonspeech mixtures. Speech Communication 1999,27(3-4):281-298. 10.1016/S0167-6393(98)00083-1
Nakatani T, Okuno HG: Harmonic sound stream segregation using localization and its application to speech stream segregation. Speech Communication 1999,27(3):209-222. 10.1016/S0167-6393(98)00079-X
Brown GJ, Wang DL: Separation of speech by computational auditory scene analysis. In Speech Enhancement: What's New?. Edited by: Benesty J, Makino S, Chen J. Springer, New York, NY, USA; 2005:371-402.
Darwin CJ, Carlyon RP: Auditory grouping. In The Handbook of Perception and Cognition. Volume 6. Edited by: Moore BCJ. Academic Press, Orlando, Fla, USA; 1995:387-424. chapter Hearing
Wang DL, Brown GJ: Separation of speech from interfering sounds based on oscillatory correlation. IEEE Transactions on Neural Networks 1999,10(3):684-697. 10.1109/72.761727
Hu G, Wang DL: Monaural speech segregation based on pitch tracking and amplitude modulation. IEEE Transactions on Neural Networks 2004,15(5):1135-1150. 10.1109/TNN.2004.832812
Jang GJ, Lee TW: A probabilistic approach to single channel blind signal separation. Proceedings of Advances in Neural Information Processing Systems (NIPS '02), December 2002, Vancouver, British Columbia, Canada 1173-1180.
Fevotte C, Godsill SJ: A Bayesian approach for blind separation of sparse sources. IEEE Transaction on Speech and Audio Processing 2005,4(99):1-15.
Girolami M: A variational method for learning sparse and overcomplete representations. Neural Computation 2001,13(11):2517-2532. 10.1162/089976601753196003
Lee T-W, Lewicki MS, Girolami M, Sejnowski TJ: Blind source separation of more sources than mixtures using overcomplete representations. IEEE Signal Processing Letters 1999,6(4):87-90. 10.1109/97.752062
Beierholm T, Pedersen BD, Winther O: Low complexity Bayesian single channel source separation. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 5: 529-532.
Roweis S: One microphone source separation. Proceedings of Advances in Neural Information Processing Systems (NIPS '00), October-November 2000, Denver, Colo, USA 793-799.
Reyes-Gomez MJ, Ellis DPW, Jojic N: Multiband audio modeling for single-channel acoustic source separation. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 5: 641-644.
Reddy AM, Raj B: A minimum mean squared error estimator for single channel speaker separation. Proceedings of the 8th International Conference on Spoken Language Processing (INTERSPEECH '04), October 2004, Jeju Island, Korea 2445-2448.
Kristjansson T, Attias H, Hershey J: Single microphone source separation using high resolution signal reconstruction. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 2: 817-820.
Rowies ST: Factorial models and refiltering for speech separation and denoising. Proceedings of the 8th European Conference on Speech Communication and Technology (EUROSPEECH '03), September 2003, Geneva, Switzerland 7: 1009-1012.
Virtanen T, Klapuri A: Separation of harmonic sound sources using sinusoidal modeling. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '00), June 2000, Istanbul, Turkey 2: 765-768.
Quatieri TF, Danisewicz RG: An approach to co-channel talker interference suppression using a sinusoidal model for speech. IEEE Transactions on Acoustics, Speech, and Signal Processing 1990,38(1):56-69. 10.1109/29.45618
Wan EA, Nelson AT: Neural dual extended Kalman filtering: applications in speech enhancement and monaural blind signal separation. Proceedings of the 7th IEEE Workshop on Neural Networks for Signal Processing (NNSP '97), September 1997, Amelia Island, Fla, USA 466-475.
Hopgood JR, Rayner PJW: Single channel nonstationary stochastic signal separation using linear time-varying filters. IEEE Transactions on Signal Processing 2003,51(7):1739-1752. 10.1109/TSP.2003.812837
Balan R, Jourjine A, Rosca J: AR processes and sources can be reconstructed from degenerative mixtures. Proceedings of the 1st International Workshop on Independent Component Analysis and Signal Separation (ICA '99), January 1999, Aussois, France 467-472.
Rouat J, Liu YC, Morissette D: A pitch determination and voiced/unvoiced decision algorithm for noisy speech. Speech Communication 1997,21(3):191-207. 10.1016/S0167-6393(97)00002-2
Chazan D, Stettiner Y, Malah D: Optimal multi-pitch estimation using the EM algorithm for co-channel speech separation. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '93), April 1993, Minneapolis, Minn, USA 2: 728-731.
Wu M, Wang DL, Brown GJ: A multipitch tracking algorithm for noisy speech. IEEE Transactions on Speech and Audio Processing 2003,11(3):229-241. 10.1109/TSA.2003.811539
Nishimoto T, Sagayama S, Kameoka H: Multi-pitch trajectory estimation of concurrent speech based on harmonic GMM and nonlinear Kalman filtering. Proceedings of the 8th International Conference on Spoken Language Processing (INTERSPEECH '04), October 2004, Jeju Island, Korea 1: 2433-2436.
Tolonen T, Karjalainen M: A computationally efficient multipitch analysis model. IEEE Transactions on Speech and Audio Processing 2000,8(6):708-716. 10.1109/89.876309
Kwon Y-H, Park D-J, Ihm B-C: Simplified pitch detection algorithm of mixed speech signals. Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS '00), May 2000, Geneva, Switzerland 3: 722-725.
Morgan DP, George EB, Lee LT, Kay SM: Cochannel speaker separation by harmonic enhancement and suppression. IEEE Transactions on Speech and Audio Processing 1997,5(5):407-424. 10.1109/89.622561
Radfar MH, Dansereau RM, Sayadiyan A: Performance evaluation of three features for model-based single channel speech separation problem. Proceedings of the 9th International Conference on Spoken Language Processing (INTERSPEECH '06), September 2006, Pittsburgh, Pa, USA 2610-2613.
Hu G, Wang D: Auditory segmentation based on onset and offset analysis. to appear in IEEE Transactions on Audio, Speech, and Language Processing
Ellis D: Model-based scene analysis. In Computational Auditory Scene Analysis: Principles, Algorithms, and Applications. Edited by: Wang D, Brown G. Wiley/IEEE Press, New York, NY, USA; 2006.
Parsons TW: Separation of speech from interfering speech by means of harmonic selection. Journal of the Acoustical Society of America 1976,60(4):911-918. 10.1121/1.381172
de Cheveigné A, Kawahara H: Multiple period estimation and pitch perception model. Speech Communication 1999,27(3):175-185. 10.1016/S0167-6393(98)00074-0
Weintraub M: A computational model for separating two simultaneous talkers. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '86), April 1986, Tokyo, Japan 11: 81-84.
Hanson BA, Wong DY: The harmonic magnitude suppression (HMS) technique for intelligibility enhancement in the presence of interfering speech. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '84), March 1984, San Diego, Calif, USA 2: 18A. 5. 1-18A. 5. 4.
Kanjilal PP, Palit S: Extraction of multiple periodic waveforms from noisy data. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '94), April 1994, Adelaide, SA, Australia 2: 361-364.
Every MR, Szymanski JE: Separation of synchronous pitched notes by spectral filtering of harmonics. IEEE Transactions on Audio, Speech and Language Processing 2006,14(5):1845-1856.
Maher RC, Beauchamp JW: Fundamental frequency estimation of musical signals using a two-way mismatch procedure. Journal of the Acoustical Society of America 1994,95(4):2254-2263. 10.1121/1.408685
Karjalainen M, Tolonen T: Multi-pitch and periodicity analysis model for sound separation and auditory scene analysis. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '99), March 1999, Phoenix, Ariz, USA 2: 929-932.
Cooke M: Modeling auditory processing and organization, Doctoral thesis.
McAulay RJ, Quatieri TF: Sinusoidal coding. In Speech Coding and Synthesis. Edited by: Kleijn W, Paliwal K. Elsevier, New York, NY, USA; 1995.
Quatieri TF: Discrete-Time Speech Signal Processing Principle and Practice. Prentice-Hall, Englewood Cliffs, NJ, USA; 2001.
Yair E, Medan Y, Chazan D: Super resolution pitch determination of speech signals. IEEE Transactions on Signal Processing 1991,39(1):40-48. 10.1109/78.80763
Martin P: Comparison of pitch detection by cepstrum and spectral comb analysis. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '82), May 1982, Paris, France 7: 180-183.
Meddis R, Hewitt M: Virtual pitch and phase sensitivity of a computer model of the auditory periphery I: pitch identification. Journal of the Acoustical Society of America 1991,89(6):2866-2882. 10.1121/1.400725
Meddis R, O'Mard L: A unitary model of pitch perception. Journal of the Acoustical Society of America 1997,102(3):1811-1820. 10.1121/1.420088
Chandra N, Yantorno RE: Usable speech detection using the modified spectral autocorrelation peak to valley ratio using the LPC residual. Proceedings of 4th IASTED International Conference on Signal and Image Processing, August 2002, Kaua'i Marriott, Hawaii, USA 146-149.
Mahgoub YA, Dansereau RM: Voicing-state classification of co-channel speech using nonlinear state-space reconstruction. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '05), March 2005, Philadelphia, Pa, USA 1: 409-412.
Kizhanatham AR, Chandra N, Yantorno RE: Co-channel speech detection approaches using cyclostationarity or wavelet transform. Proceedings of 4th IASTED International Conference on Signal and Image Processing, August 2002, Kaua'i Marriott, Hawaii, USA
Benincasa DS, Savic MI: Voicing state determination of co-channel speech. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '98), May 1998, Seattle, Wash, USA 2: 1021-1024.
Radfar MH, Dansereau RM, Sayadiyan A: A joint identification-separation technique for single channel speech separation. Proceedings of the 12th IEEE Digital Signal Processing Workshop (DSP '06), September 2006, Grand Teton National Park, Wyo, USA 76-81.
Radfar MH, Sayadiyan A, Dansereau RM: A new algorithm for two-talker pitch tracking in single channel paradigm. Proceedings of International Conference on Signal Processing (ICSP '06), November 2006, Guilin, China
Nadas A, Nahamoo D, Picheny MA: Speech recognition using noise-adaptive prototypes. IEEE Transactions on Acoustics, Speech, and Signal Processing 1989,37(10):1495-1503. 10.1109/29.35387
Paliwal KK, Alsteris LD: On the usefulness of STFT phase spectrum in human listening tests. Speech Communication 2005,45(2):153-170. 10.1016/j.specom.2004.08.001
Paul DB: The spectral envelope estimation vocoder. IEEE Transactions on Acoustics, Speech, and Signal Processing 1981,29(4):786-794. 10.1109/TASSP.1981.1163643
de Boor C: A Practical Guide to Splines. Springer, New York, NY, USA; 1978.
Talkin D: A robust algorithm for pitch tracking (RAPT). In Speech Coding and Synthesis. Edited by: Kleijn W, Paliwal K. Elsevier, Amsterdam, The Netherlands; 1995:495-518.
Gersho A, Gray RM: Vector Quantization and Signal Compression. Kluwer Academic, Norwell, Mass, USA; 1992.
Chu WC: Vector quantization of harmonic magnitudes in speech coding applications - a survey and new technique. EURASIP Journal on Applied Signal Processing 2004,2004(17):2601-2613. 10.1155/S1110865704407161
Wang D: On ideal binary mask as the computational goal of auditory scene analysis. In Speech Separation by Humans and Machines. Edited by: Divenyi P. Kluwer Academic, Norwell, Mass, USA; 2005:181-197.
Naylor JA, Boll SF: Techniques for suppression of an interfering talker in co-channel speech. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '87), April 1987, Dallas, Tex, USA 1: 205-208.