Abstract
Employing automatic speech recognition systems in hands-free communication applications is accompanied by perfomance degradation due to background noise and, in particular, due to reverberation. These two kinds of distortion alter the shape of the feature vector trajectory extracted from the microphone signal and consequently lead to a discrepancy between training and testing conditions for the recognizer. In this chapter we present a feature enhancement approach aiming at the joint compensation of noise and reverberation to improve the performance by restoring the training conditions. For the enhancement we concentrate on the logarithmic mel power spectral coefficients as features, which are computed at an intermediate stage to obtain the widely used mel frequency cepstral coefficients. The proposed technique is based on a Bayesian framework, to attempt to infer the posterior distribution of the clean features given the observation of all past corrupted features. It exploits information from a priori models describing the dynamics of clean speech and noise-only feature vector trajectories as well as from an observation model relating the reverberant noisy to the clean features. The observation model relies on a simplified stochastic model of the room impulse response (RIR) between the speaker and the microphone, having only two parameters, namely RIR energy and reverberation time, which can be estimated from the captured microphone signal. The performance of the proposed enhancement technique is finally experimentally studied by means of recognition accuracy obtained for a connected digits recognition task under different noise and reverberation conditions using the Aurora 5 database.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Avargel, Y., Cohen, I.: On multiplicative transfer function approximation in the short-time Fourier transform domain. IEEE Signal Processing Letters 14(5), 337–340 (2007)
Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with Applications to Tracking and Navigation: Theory, Algorithms, and Software. Wiley, New York (2001)
Couvreur, L., Couvreur, C.: Blind model selection for automatic speech recognition in reverberant environments. Journal of VLSI Signal Processing 36(2/3), 189–203 (2004)
Delcroix, M., Hikichi, T., Miyoshi, M.: On the use of lime dereverberation algorithm in an acoustic environment with a noise source. Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 1, I–I (2006)
Delcroix, M., Nakatani, T., Watanabe, S.: Static and dynamic variance compensation for recognition of reverberant speech with dereverberation preprocessing. IEEE Transactions on Audio, Speech, and Language Processing 17(2), 324–334 (2009)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 39(1), 1–38 (1977)
Droppo, J., Acero, A.: Noise robust speech recognition with a switching linear dynamic model. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. I–953–6 vol.1 (2004)
ETSI: ETSI standard document, Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Advanced front-end feature extraction algorithm; Compression algorithms, ETSI ES 202 050 V1.1.5 (2007-01)
ETSI: ETSI standard document, Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms, ETSI ES 201 108 V1.1.3 (2003-09)
Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech and Language 12(2), 75–98 (1998)
Gales, M.J.F., Woodland, P.C.: Mean and variance adaptation within the MLLR framework. Computer Speech and Language 10(4), 249–264 (1996)
Gannot, S., Moonen, M.: Subspace methods for multi-microphone speech dereverberation. EURASIP Journal on Applied Signal Processing 11, 1074–1090 (2003)
Gürelli, M., Nikias, C.: EVAM: an eigenvector-based algorithm for multichannel blind deconvolution of input colored signals. IEEE Transactions on Signal Processing 43(1), 134–149 (1995)
Habets, E.: Single- and multi-microphone speech dereverberation using spectral enhancement. Ph.D. thesis, Technische Universiteit Eindhoven (2007)
Hermansky, H., Morgan, N.: RASTA processing of speech. IEEE Transactions on Speech and Audio Processing 2(4), 578–589 (1994)
Hirsch, H.: Aurora-5 experimental framework for the performance evaluation of speech recognition in case of a hands-free speech input in noisy environments. Tech. rep., Niederrhein University of Applied Sciences (2007)
Hirsch, H.G., Finster, H.: The simulation of realistic acoustic input scenarios for speech recognition systems. In: Proc. of Annual Conference of the International Speech Communication Association (Interspeech), pp. 2697–2700 (2005)
Hirsch, H.G., Finster, H.: A new approach for the adaptation of HMMs to reverberation and background noise. Speech Commununication 50(3), 244–263 (2008)
Julier, S.J., Jeffrey, Uhlmann, K.: Unscented filtering and nonlinear estimation. In: Proceedings of the IEEE, pp. 401–422 (2004)
Kennedy, R., Radlovic, B.: Iterative cepstrum-based approach for speech dereverberation. In: Proc. of International Symposium on Signal Processing and its Applications (ISSPA), vol. 1, pp. 55–58 vol.1 (1999)
Kingsbury, B.E.D., Morgan, N.: Recognizing reverberant speech with RASTA-PLP. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2, pp. 1259–1262 (1997)
Kinoshita, K., Delcroix, M., Nakatani, T., Miyoshi, M.: Suppression of late reverberation effect on speech signal using long-term multiple-step linear prediction. IEEE Transactions on Audio, Speech, and Language Processing 17(4), 534–545 (2009)
Krueger, A., Haeb-Umbach, R.: Model-based feature enhancement for reverberant speech recognition. IEEE Transactions on Audio, Speech, and Language Processing 18(7), 1692–1707 (2010)
Krueger, A., Leutnant, V., Haeb-Umbach, R., Marcel, A., Bloemer, J.: On the initialisation of dynamic models for speech features. In: Proc. of ITG Fachtagung Sprachkommunikation (2010)
Langhans, T., Strube, H.: Speech enhancement by nonlinear multiband envelope filtering. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 7, pp. 156–159 (1982)
Lebart, K., Boucher, J., Denbigh, P.: A new method based on spectral subtraction for speech dereverberation. Acta Acustica United with Acustica 87, 359–366(8) (2001)
Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language 9(2), 171–185 (1995)
Löllmann, H.W., Vary, P.: Low delay noise reduction and dereverberation for hearing aids. In: EURASIP Journal on Advances in Signal Processing (2009)
Murphy, K.: Switching Kalman filters. Tech. rep., U.C. Berkeley (1998)
Neely, S.T., Allen, J.B.: Invertibility of a room impulse response. Journal of the Acoustical Society of America 66(1), 165–169 (1979)
Qian, S., Chen, D.: Discrete Gabor transform. IEEE Transactions on Signal Processing 41(7), 2429–2438 (1993)
Ratnam, R., Jones, D., O’Brien W.D., J.: Fast algorithms for blind estimation of reverberation time. IEEE Signal Processing Letters 11(6), 537–540 (2004)
Ratnam, R., Jones, D.L., Wheeler, B.C., O’Brien, W.D., Lansing, C.R., Feng, A.S.: Blind estimation of reverberation time. Journal of the Acoustical Society of America 114(5), 2877–2892 (2003)
Raut, C.K., Nishimoto, T., , Sagayama, S.: Model adaptation by state splitting of HMM for long reverberation. In: Proc. of Annual Conference of the International Speech Communication Association (Interspeech) (Sep 2005)
Rosenberg, A.E., Lee, C.H., Soong, F.K.: Cepstral channel normalization techniques for HMM-based speaker verification. In: Proc. of International Conference on Spoken Language Processing (ICSLP), pp. 1835–1838 (1994)
Sehr, A., Kellerman, W.: A new concept for feature-domain dereverberation for robust distant-talking ASR. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. IV–369–IV–372 (2007)
Subramaniam, S., Petropulu, A., Wendt, C.: Cepstrum-based deconvolution for speech dereverberation. IEEE Transactions on Speech and Audio Processing 4(5), 392–396 (1996)
Unoki, M., Sakata, K., Furukawa, M., Akagi, M.: A speech dereverberation method based on the MTF concept in power envelope restoration. Acoustical Science and Technology 25(4), 243–254 (2004)
Wu, M., Wang, D.: A two-stage algorithm for one-microphone reverberant speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing 14(3), 774–784 (2006)
Yegnanarayana, B., Mahadeva Prasanna, S., Sreenivasa Rao, K.: Speech enhancement using excitation source information. In: Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. I–541–I–544 (2002)
Yegnanarayana, B., Murthy, P.: Enhancement of reverberant speech using LP residual signal. IEEE Transactions on Speech and Audio Processing 8(3), 267–281 (2000)
Yoshioka, T., Nakatani, T., Miyoshi, M.: Integrated speech enhancement method using noise suppression and dereverberation. IEEE Transactions on Audio, Speech, and Language Processing 17(2), 231–246 (2009)
Young, S.J., Evermann, G., Gales, M.J.F., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.C.: The HTK Book, version 3.4. Cambridge University Engineering Department, Cambridge, UK (2006)
Zhang, Z., Furui, S.: Piecewise-linear transformation-based hmm adaptation for noisy speech. Speech Commununication 42(1), 43–58 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Krueger, A., Haeb-Umbach, R. (2011). A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition. In: Kolossa, D., Häb-Umbach, R. (eds) Robust Speech Recognition of Uncertain or Missing Data. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21317-5_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-21317-5_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21316-8
Online ISBN: 978-3-642-21317-5
eBook Packages: EngineeringEngineering (R0)