Home

Pushing the Envelope—Aside

Nelson Morgan; Qifeng Zhu; Andreas Stolcke; Kemal Sönmez; Sunil Sivadas; Takahiro Shinozaki; Mari Ostendorf; Pratibha Jain; Hynek Hermansky; Daniel P. W. Ellis; George Doddington; Barry Chen; Özgür Çetin; Hervé Bourlard; Marios Athineos

Title:
Pushing the Envelope—Aside
Author(s):
Morgan, Nelson
Zhu, Qifeng
Stolcke, Andreas
Sönmez, Kemal
Sivadas, Sunil
Shinozaki, Takahiro
Ostendorf, Mari
Jain, Pratibha
Hermansky, Hynek
Ellis, Daniel P. W.
Doddington, George
Chen, Barry
Çetin, Özgür
Bourlard, Hervé
Athineos, Marios
Date:
Type:
Articles
Department:
Electrical Engineering
Volume:
22
Book/Journal Title:
IEEE Signal Processing Magazine
Abstract:
Despite successes, there are still significant limitations to speech recognition performance, particularly for conversational speech and/or for speech with significant acoustic degradations from noise or reverberation. For this reason, authors have proposed methods that incorporate different (and larger) analysis windows, which are described in this article. Note in passing that we and many others have already taken advantage of processing techniques that incorporate information over long time ranges, for instance for normalization (by cepstral mean subtraction as stated in B. Atal (1974) or relative spectral analysis (RASTA) based in H. Hermansky and N. Morgan (1994)). They also have proposed features that are based on speech sound class posterior probabilities, which have good properties for both classification and stream combination.
Subject(s):
Artificial intelligence
Communication
Publisher DOI:
http://dx.doi.org/10.1109/MSP.2005.1511826
Item views:
68
Metadata:
text | xml

In Partnership with the Center for Digital Research and Scholarship at Columbia University Libraries/Information Services | Terms of Use