ITEM METADATA RECORD
Title: Localized Spectro-Temporal Features for Noise-Robust Speech Recognition
Authors: Kovács, György
Tóth, László
Issue Date: 2010
Host Document: COMPUTATIONAL CYBERNETICS AND TECHNICAL INFORMATICS. INTERNATIONAL JOINT CONFERENCE. 2010. (ICCC-CONTI 2010) pages:481-485
Conference: IEEE International Joint Conferences on Computational Cybernetics and Technical Informatics location:Timisoara date:27/29 May 2010
Abstract: In speech recognition there has been a trend to incorporate more and more knowledge about human hearing into the feature extraction step. One such approach is the application of localized spectro-temporal analysis, which is inspired by neurophysiological studies. Here we experiment with extracting features from the patches of the widely used criticial-band log-energy spectrum by applying
the two-dimensional cosine transform. Compared to earlier similar studies with the spectrogram representation, we find that our method is not worse, and faster. In experiments with noisy speech the proposed representation proves more noise-robust than the conventional mel-frequency cepstral features.
Publication status: published
KU Leuven publication type: IC
Appears in Collections:Non-KU Leuven Association publications

Files in This Item:
File Description Status SizeFormat
ICCC-CONTI1.pdf Published 627KbAdobe PDFView/Open

 


All items in Lirias are protected by copyright, with all rights reserved.