On the efficiency of classical RASTA filtering for continuous speech recognition: Keeping the balance between acoustic pre-processing and acoustic modelling
From MaRDI portal
Publication:4794980
DOI10.1016/S0167-6393(02)00030-4zbMath1006.68936MaRDI QIDQ4794980
Publication date: 20 February 2003
Published in: Speech Communication (Search for Journal in Brave)
continuous speech recognitionchannel normalisationclassical RASTA filteringphase-corrected RASTAtelephone lines
Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99) Natural language processing (68T50)
This page was built for publication: On the efficiency of classical RASTA filtering for continuous speech recognition: Keeping the balance between acoustic pre-processing and acoustic modelling