Abstract
Spectro-temporal feature extraction and multi-band processing were both designed to make the speech recognizers more robust. Although they have been used for a long time now, very few attempts have been made to combine them. This is why here we integrate two spectro-temporal feature extraction methods into a multi-band framework. We assess the performance of our spectro-temporal feature sets both individually (as a baseline) and in combination with multi-band processing in phone recognition tasks on clean and noise contaminated versions of the TIMIT dataset. Our results show that multi-band processing clearly outperforms the baseline feature recombination method in every case tested. This improved performance can also be further enhanced by using the recently introduced technology of deep neural nets (DNNs).
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
Bourlard, H., Dupont, S.: A New ASR Approach Based on Independent Processing and Recombination of Partial Frequency Bands. In: ICSLP, pp. 426–429 (1996)
Hermansky, H., Timbrewala, S., Pavel, M.: Towards ASR On Partially Corrupted Speech. In: ICSLP, pp. 464–465 (1996)
Hagen, A., Morris, A., Bourlard, H.: Subband-Based Speech Recognition in Noisy Conditions The Full Combination Approach. Research Report, IDIAP (1998)
Janin, A., Ellis, D., Morgan, N.: Multi-Stream Speech Recognition: Ready for Prime Time? In: Eurospeech 1999, pp. 591–594 (1999)
Cerisara, C., Fohr, D.: Multi-band Automatic Speech Recognition. Computer Speech and Language 15, 151–174 (2001)
Kovács, G., Tóth, L.: Phone Recognition Experiments with 2D DCT Spectro-temporal Features. In: SACI 2011, pp. 143–146 (2011)
Kleinschmidt, M., Gelbart, D.: Improving Word Accuracy with Gabor Feature Extraction. In: ICSLP, pp. 25–28 (2002)
Kovács, G., Tóth, L.: The Joint Optimization of Spectro-temporal Features and Neural Net Classifiers. In: TSD 2013, pp. 552–559 (2013)
Mesgarani, N., Thomas, S., Hermansky, H.: A multistream multiresolution framework for phoneme recognition. In: INTERSPEECH, pp. 318–321 (2010)
Zhao, S.Y., Ravuri, S.V., Morgan, N.: Multi-stream to many-stream: using spectro-temporal features for ASR. In: INTERSPEECH, pp. 2951–2954 (2009)
Hinton, G., et al.: Deep Neural Networks for Acoustic Modeling in Speech Recognition. IEEE Signal Processing Magazine 29, 82–97 (2012)
Okawa, S., Bocchieri, E., Potamianos, A.: Multi-band Speech Recognition in Noisy Environments. In: ICASSP, pp. 641–644 (1998)
Hagen, A., Morris, A., Bourlard, H.: From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR. ISCA ASR2000 Tutorial and Research Workshop (2000)
Hagen, A., Bourlard, H., Morris, A.: Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR. In: ICASSP, pp. 257–260 (2001)
Morris, A., Hagen, A., Glotin, H., Bourlard, H.: Multi-stream adaptive evidence combination for noise robust ASR. Speech Communication 34, 25–40 (2001)
Hagen, A., Neto, J.P.: Multi-stream Processing Using Context-independent and Context-dependent Hybrid Systems. In: ICASSP, pp. 277–280 (2003)
Lamel, L.F., Kassel, R., Seneff, S.: Speech database development: Design and analysis of the acoustic-phonetic corpus. In: DARPA Speech Recognition Workshop, pp. 100–109 (1986)
Young, S.J., et al.: The HTK book version 3.4. Cambridge University Press, Cambridge (2006)
Hagen, A., Morris, A., Bourlard, H.: From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR. In: ISCA ASR2000 Tutorial and Research Workshop (2000)
Varga, A., Steeneken, H.: Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication 12, 247–251 (1993)
Hirsch, H.-G.: FaNT: Filtering and Noise-Adding Tool Retrieved March 22 (2010), http://dnt.kr.hs-niederrhein.de/download.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kovács, G., Tóth, L., Grósz, T. (2014). Robust Multi-Band ASR Using Deep Neural Nets and Spectro-temporal Features. In: Ronzhin, A., Potapova, R., Delic, V. (eds) Speech and Computer. SPECOM 2014. Lecture Notes in Computer Science(), vol 8773. Springer, Cham. https://doi.org/10.1007/978-3-319-11581-8_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-11581-8_48
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11580-1
Online ISBN: 978-3-319-11581-8
eBook Packages: Computer ScienceComputer Science (R0)