A proposed method to improve the WER of an ASR system in the noisy reverberant room

DOI10.1016/J.JFRANKLIN.2023.11.039OpenAlexW4389375199MaRDI QIDQ6150065

Mohammad Javad Emadi, Hamid Sheikhzadeh, Mohammad Ebrahim Sadeghi

Publication date: 6 February 2024

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jfranklin.2023.11.039

zbMATH Keywords

beamformingspherical arraydereverberationSHDspeech improvementWER

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cites Work

• Acoustic MIMO signal processing
• Robust Multichannel Linear Prediction for Online Speech Dereverberation Using Weighted Householder Least Squares Lattice Adaptive Filter
• Blind Localization of Early Room Reflections Using Phase Aligned Spatial Correlation

This page was built for publication: A proposed method to improve the WER of an ASR system in the noisy reverberant room