Copyright © 2008 The Institute of Electronics, Information and Communication Engineers
Special Section on Robust Speech Processing in Realistic Environments -- Papers -- Noisy Speech Recognition |
Noise Suppression Based on Multi-Model Compositions Using Multi-Pass Search with Multi-Label N-gram Models
1 The authors are with the ATR Knowledge Science Laboratories, Kyoto-fu, 619–0288 Japan. E-mail: takatoshi.jitsuhiro{at}atr.jp
We propose a noise suppression method based on multi-model compositions and multi-pass search. In real environments, input speech for speech recognition includes many kinds of noise signals. To obtain good recognized candidates, suppressing many kinds of noise signals at once and finding target speech is important. Before noise suppression, to find speech and noise label sequences, we introduce multi-pass search with acoustic models including many kinds of noise models and their compositions, their n-gram models, and their lexicon. Noise suppression is frame-synchronously performed using the multiple models selected by recognized label sequences with time alignments. We evaluated this method using the E-Nightingale task, which contains voice memoranda spoken by nurses during actual work at hospitals. The proposed method obtained higher performance than the conventional method.
Key Words: speech recognition, noise suppression, model composition, multi-pass search, E-Nightingale project
Manuscript received June 25, 2007. Manuscript revised September 14, 2007.
Reference
[1] K. Kogure, "Toward a knowledge sharing system based on understanding everyday activities and situations – Introduction to the E-Nightingale project," Proc. Workshop on Knowledge Sharing for Everyday Life 2006 (KSEL2006), pp.1–8, 2006. [2] http://www.e-nightingale.org/ [3] H. Ozaku, A. Abe, K. Sagara, N. Kuwahara, and K. Kogure, "A task analysis of nursing activities using spoken corpora," Advances in Natural Language Processing (ed. A. Gelbukh), Research in Computing Science 18, pp.125–136, Instituto Politecnico Nacional, Mexico, 2006. [4] S.F. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust. Speech Signal Process., vol.27, no.27, pp.113–120, 1979. [5] M.F.J. Gales, Model-based techniques for noise robust speech recognition, PhD Thesis, University of Cambridge. 1995. [6] J.C. Segura, A. de la Torre, M.C. Benitez, and A.M. Peinado, "Model-based compensation of the additive noise for continuous speech recognition. Experiments using the AURORA II database and tasks," Proc. EUROSPEECH2001, vol.1, pp.221–224, 2001. [7] K. Yao, K.K. Paliwal, and S. Nakamura, "Noise adaptive speech recognition based on sequential noise parameter estimation," Speech Commun., vol.42, no.1, pp.5–23, 2004. [8] M. Fujimoto and S. Nakamura, "A non-stationary noise suppression method based on particle filtering and Polyak averaging," IEICE Trans. Inf. & Syst., vol.E89-D, no.3, pp.922–930, March 2006. [9] N. Miyake, T. Takiguchi, and Y. Ariki, "Noise detection with multi-class AdaBoost," IEICE Technical Report, NLC2006-30, SP2006-86, 2006. [10] W. Herbordt, T. Horiuchi, M. Fujimoto, T. Jitsuhiro, and S. Nakamura, "Hands-free speech recognition and communication on PDAs using microphone array technology," Proc. ASRU2005, pp.302–307, 2005. [11] P.J. Moreno, Speech recognition in noisy environments, PhD Thesis, Carnegie Mellon University, Pittsburgh, Pennsylvania. 1996. [12] T. Jitsuhiro, T. Matsui, and S. Nakamura, "Automatic generation of non-uniform HMM topologies based on the MDL criterion," IEICE Trans. Inf. & Syst., vol.E87-D, no.8, pp.2121–2129, Aug. 2004. [13] J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol.2, no.2, pp.291–298, 1994. [14] M. Tonomura, T. Kosaka, and S. Matsunaga, "Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation," Comput. Speech Lang., vol.10, pp.117–132, 1996. [15] N. Kitaoka, T. Yamada, T. Takiguchi, S. Tsuge, K. Yamamoto, C. Miyajima, T. Nishiura, M. Nakayama, Y. Denda, M. Fujimoto, S. Tamura, S. Kuroiwa, K. Takeda, and S. Nakamura, "Progress report of SLP noisy speech recognition evaluation WG: Individual evaluation framework for each factor affecting recognition performance," IEICE Technical Report, NLC2006-29, SP2006-85, 2006.
CiteULike 
Connotea 
Del.icio.us What's this?
This Article 
Abstract
Full Text (PDF)
Alert me when this article is cited
Alert me if a correction is posted
Services
Email this article to a friend
Similar articles in this journal
Alert me to new issues of the journal
Add to My Personal Archive
Download to citation manager
Request Permissions
Google Scholar
Articles by JITSUHIRO, T.
Articles by KOGURE, K.
Social Bookmarking
What's this?