IEEE - Institute of Electrical and Electronics Engineers, Inc. - Analysis of phone posterior feature space exploiting class-specific sparsity and MLP-based similarity measure

2010 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2010

Author(s): Afsaneh Asaei ; Benjamin Picart ; Herve Bourlard
Sponsor(s): Signal Process. Soc.
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 March 2010
Conference Location: Dallas, TX, USA
Conference Date: 14 March 2010
Page(s): 4,886 - 4,889
ISBN (CD): 978-1-4244-4296-6
ISBN (Paper): 978-1-4244-4295-9
ISSN (CD): 1520-6149
ISSN (Electronic): 2379-190X
ISSN (Paper): 1520-6149
DOI: 10.1109/ICASSP.2010.5495121
Regular:

Class posterior distributions have recently been used quite successfully in Automatic Speech Recognition (ASR), either for frame or phone level classification or as acoustic features, which can be... View More

Advertisement