Abstract
Automatic speech recognition (ASR) systems, trained on speech signals from close-talking microphones, generally fail in recognizing far-field speech. In this paper, we present a Hilbert Envelope based feature extraction technique to alleviate the artifacts introduced by room reverberations. The proposed technique is based on modeling temporal envelopes of the speech signal in narrow sub-bands using Frequency Domain Linear Prediction (FDLP). ASR experiments on far-field speech using the proposed FDLP features show significant performance improvements when compared to other robust feature extraction techniques (average relative improvement of 43 % in word error rate).
This is a preview of subscription content, log in via an institution to check access.
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
Avendano, C.: Temporal Processing of Speech in a Time-Feature Space. Ph.D. thesis, Oregon Graduate Institute (1997)
Avendano, C., Hermansky, H.: On the Effects of Short-Term Spectrum Smoothing in Channel Normalization. IEEE Trans. Speech and Audio Proc. 5(4), 372–374 (1997)
Gelbart, D., Morgan, N.: Double the trouble: handling noise and reverberation in far-field automatic speech recognition. In: Proc. ICSLP, Colorado, USA, pp. 2185–2188 (2002)
Herre, J., Johnston, J.D.: Enhancing the Performance of Perceptual Audio Coders by using Temporal Noise Shaping (TNS). In: Proc. 101st AES Conv., Los. Angeles, USA, pp. 1–24 (1996)
Makhoul, J.: Linear Prediction: A Tutorial Review. Proc. of the IEEE 63(4), 561–580 (1975)
Athineos, M., Hermansky, H., Ellis, D.P.W.: LP-TRAPS: Linear Predictive Temporal Patterns. In: Proc. INTERSPEECH, Jeju Island, Korea, pp. 1154–1157 (2004)
Mourjopoulos, J., Hammond, J.K.: Modelling and Enhancement of Reverberant Speech using an Envelope Convolution Method. In: Proc. ICA, Boston, USA, pp. 1144–1147 (1983)
Hermansky, H.: Perceptual Linear Predictive (PLP) Analysis of Speech. J. Acoust. Soc. Am. 87(4), 1738–1752 (1990)
Hirsch, H.G., Pearce, D.: The AURORA Experimental Framework for the Performance Evaluations of Speech Recognition Systems under Noisy Conditions. In: Proc. ISCA ITRW ASR 2000, Paris, France, pp. 18–20 (2000)
Pierce, D., Gunawardana, A.: Aurora 2.0 speech recognition in noise: Update 2. In: Colorado, U.S.A. (ed.) Proc. ICSLP Session on Noise Robust Rec, Colorado, USA (2002)
The ICSI Meeting Recorder Project, http://www.icsi.berkeley.edu/Speech/mr
ICSI Room Responses, http://www.icsi.berkeley.edu/speech/papers/asru01-meansub-corr.html
Rosenberg, A.E., Lee, C., Soong, F.K.: Cepstral Channel Normalization Techniques for HMM-Based Speaker Verification. In: Proc. ICSLP, Yokohama, Japan, pp. 1835–1838 (1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thomas, S., Ganapathy, S., Hermansky, H. (2008). Hilbert Envelope Based Features for Far-Field Speech Recognition. In: Popescu-Belis, A., Stiefelhagen, R. (eds) Machine Learning for Multimodal Interaction. MLMI 2008. Lecture Notes in Computer Science, vol 5237. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85853-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-85853-9_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85852-2
Online ISBN: 978-3-540-85853-9
eBook Packages: Computer ScienceComputer Science (R0)