SNR estimation based on amplitude modulation analysis with applications to noise suppression
- 9 July 2003
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 11 (3), 184-192
- https://doi.org/10.1109/tsa.2003.811542
Abstract
A single-microphone noise suppression algorithm is described that is based on a novel approach for the estimation of the signal-to-noise ratio (SNR) in different frequency channels: The input signal is transformed into neurophysiologically-motivated spectro-temporal input features. These patterns are called amplitude modulation spectrograms (AMS), as they contain information of both center frequencies and modulation frequencies within each 32 ms-analysis frame. The different representations of speech and noise in AMS patterns are detected by a neural network, which estimates the present SNR in each frequency channel. Quantitative experiments show a reliable estimation of the SNR for most types of nonspeech background noise. For noise suppression, the frequency bands are attenuated according to the estimated present SNR using a Wiener filter approach. Objective speech quality measures, informal listening tests, and the results of automatic speech recognition experiments indicate a substantial benefit from AMS-based noise suppression, in comparison to unprocessed noisy speech.Keywords
This publication has 23 references indexed in Scilit:
- Estimation of the signal-to-noise ratio with amplitude modulation spectrogramsSpeech Communication, 2002
- Syllable intelligibility for temporally filtered LPC cepstral trajectoriesThe Journal of the Acoustical Society of America, 1999
- Noise reduction for speech signals by operations on the modulation frequency spectrumThe Journal of the Acoustical Society of America, 1999
- A neural model for auditory scene analysisThe Journal of the Acoustical Society of America, 1999
- Frequency selectivity in amplitude-modulation processingThe Journal of the Acoustical Society of America, 1999
- Frequency and periodicity are represented in orthogonal maps in the human auditory cortex: evidence from magnetoencephalographyJournal of Comparative Physiology A, 1997
- Modeling auditory processing of amplitude modulation. I. Detection and masking with narrow-band carriersThe Journal of the Acoustical Society of America, 1997
- Modeling auditory processing of amplitude modulation. II. Spectral and temporal integrationThe Journal of the Acoustical Society of America, 1997
- Speech Recognition with Primarily Temporal CuesScience, 1995
- Effect of temporal envelope smearing on speech receptionThe Journal of the Acoustical Society of America, 1994