Sciweavers

Share
ICASSP
2008
IEEE
10 years 2 months ago
Towards the use of full covariance models for missing data speaker recognition
This work investigates the use of missing data techniques for noise robust speaker identification. Most previous work in this field relies on the diagonal covariance assumption ...
Marco Kühne, Daniel Pullella, Roberto Togneri...
ICASSP
2008
IEEE
10 years 2 months ago
Can voice quality improve mandarin tone recognition?
We investigate several measures of voice quality (VQ) to improve tone recognition in Mandarin Chinese. We find that band energy measures such as Spectral Balance (Sluijter and va...
Dinoj Surendran, Gina-Anne Levow
ICASSP
2008
IEEE
10 years 2 months ago
Effective error prediction using decision tree for ASR grammar network in call system
CALL (Computer Assisted Language Learning) systems using ASR (Automatic Speech Recognition) for second language learning have received increasing interest recently. However, it st...
Hongcui Wang, Tatsuya Kawahara
ICASSP
2008
IEEE
10 years 2 months ago
Confidence scores for acoustic model adaptation
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. ...
Christian Gollan, Michiel Bacchiani
ICASSP
2008
IEEE
10 years 2 months ago
Using variational bayes free energy for unsupervised voice activity detection
This paper addresses the problem of Voice Active Detection (VAD) in noisy environments. We introduce Variational Bayes approach to EM for classification to replace the heuristic ...
David Cournapeau, Tatsuya Kawahara
ICASSP
2008
IEEE
10 years 2 months ago
Implementing communications systems on an SDR SoC
Software Defined Radios (SDRs) offer a programmable and dynamically reconfigurable method of reusing hardware to implement the physical layer processing of multiple communications...
John Glossner, Daniel Iancu, Mayan Moudgill, Sanja...
ICASSP
2008
IEEE
10 years 2 months ago
A comparison of phone and grapheme-based spoken term detection
Dong Wang, Joe Frankel, Javier Tejedor, Simon King
ICASSP
2008
IEEE
10 years 2 months ago
Dual-microphone speech dereverberation using GARCH modeling
In this paper, we develop a dual-microphone speech dereverberation algorithm for noisy environments, which is aimed at suppressing late reverberation and background noise. The spe...
Ari Abramson, Emanuel A. P. Habets, Sharon Gannot,...
ICASSP
2008
IEEE
10 years 2 months ago
Maximum-likelihood period estimation from sparse, noisy timing data
Robby G. McKilliam, I. Vaughan L. Clarkson
ICASSP
2008
IEEE
10 years 2 months ago
Modulation analysis of speech through orthogonal FIR filterbank optimization
Newborns must learn to structure incoming acoustic information into segments, words, phrases, etc., before they can start to learn language. This process is thought to rely on mod...
Jonathan Le Roux, Hirokazu Kameoka, Nobutaka Ono, ...
books