Assessing local noise level estimation methods: Application to noise robust ASR

DOI10.1016/S0167-6393(00)00051-0MaRDI QIDQ4794920zbMATH OpenFDO

Authors Christophe Ris, Stéphane Dupont

Publication date 20 February 2003

Published in Speech Communication (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0167-6393(00)00051-0

zbMATH Keywords

missing datanoise level estimationnoise reductionrobust automatic speech recognitionspectral subtraction

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Spectral reconstruction and noise model estimation based on a masking model for noise robust speech recognition
• Estimation of the signal-to-noise ratio with amplitude modulation spectrograms
• Multitaper smoothed minimum statistics noise power estimation
• Low complexity DFT-domain noise PSD tracking using high-resolution periodograms
• Sub-band SNR estimation using auditory feature processing

Cited in

(5)

• Spectral reconstruction and noise model estimation based on a masking model for noise robust speech recognition
• Multitaper smoothed minimum statistics noise power estimation
• Estimation of the signal-to-noise ratio with amplitude modulation spectrograms
• Sub-band SNR estimation using auditory feature processing
• Likelihood-maximizing-based multiband spectral subtraction for robust speech recognition

This page was built for publication: Assessing local noise level estimation methods: Application to noise robust ASR

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4794920)