IEEE - Institute of Electrical and Electronics Engineers, Inc. - Investigating deep neural network based transforms of robust audio features for LVCSR

ICASSP 2013 - IEEE International Conference on Acoustics, Speech and Signal Processing

Author(s): Enrico Bocchieri ; Dimitrios Dimitriadis
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 May 2013
Conference Location: Vancouver, BC, Canada
Conference Date: 26 May 2013
Page(s): 6,709 - 6,713
ISBN (Electronic): 978-1-4799-0356-6
ISSN (Paper): 1520-6149
DOI: 10.1109/ICASSP.2013.6638960
Regular:

Micro-modulation components such as the formant frequencies are very important characteristics of spoken speech that have allowed great performance improvements in small-vocabulary ASR tasks. Yet... View More

Advertisement