Abstract
Amplitude Modulation spectrogram (AMS) can reflect the orthogonality between the “periodotopical” organization and the tonotopical organization in neurons, and can be used as a reliable discrimination between speech and noise. This paper presents a novel approach of robust speech recognition by using AMS and Spectrum Subtraction with Confidence Interval Test. By dynamic using Confidence Interval Test, the error of estimated SNR was decreased. Experiment results show the proposed method yield good performance for attenuating the effect of noises and can improve the robustness of ASR.
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
References
Xin M, Zhou WD (2006) Robust speech feature extraction based on dynamic minimum subband spectral subtraction. Lecture Notes in Control and Information Sciences 345: 1056–1061
Flores JAN, Young SJ (1994) Continuous speech recognition in noise using spectral subtraction and HMM adaptation. ICASSP 1:409–412
Raj B, Seltzer M, and Stern R (2000) Reconstruction of damaged spectrographic features for robust speech recognition. Proceedings of the International Conference on Spoken Language Processing 1: 375–360
Gales, MJF, Young SJ (1996) Robust continuous speech recognition using parallel model combination. IEEE Transactions on Speech and Audio Processing 4, 352–359.
Langner G, Sams M, Heil P, et al. (1997) Frequency and periodicity are represented in orthogonal maps in the human auditory cortex: Evidence from magnetoencephalography. J. Comp. Physiol.181: 665–676
Hermansky H (1997) The Modulation Spectrum in Automatic Recognition of Speech. IEEE Workshop on Automatic Speech Recognition and Understanding 140–147
Tchorz J, Kollmeier B (2003) SNR Estimation Based on Amplitude Modulation Analysis With Applications to Noise Suppression. IEEE Transactions on Speech and Audio Processing 11: 184–192
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, X., Zhou, W. (2008). AMS Based Spectrum Subtraction Algorithm with Confidence Interval Test. In: Peng, Y., Weng, X. (eds) 7th Asian-Pacific Conference on Medical and Biological Engineering. IFMBE Proceedings, vol 19. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-79039-6_98
Download citation
DOI: https://doi.org/10.1007/978-3-540-79039-6_98
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-79038-9
Online ISBN: 978-3-540-79039-6
eBook Packages: EngineeringEngineering (R0)