Sciweavers

509 search results - page 96 / 102
» icassp 2008
Sort
View
77
Voted
ICASSP
2008
IEEE
15 years 4 months ago
Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments
Automatic Speech Recognition (ASR) systems continue to make errors during search when handling various phenomena including noise, pronunciation variation, and out of vocabulary (O...
Christopher M. White, Geoffrey Zweig, Lukas Burget...
ICASSP
2008
IEEE
15 years 4 months ago
Wavelet-domain compressive signal reconstruction using a Hidden Markov Tree model
Compressive sensing aims to recover a sparse or compressible signal from a small set of projections onto random vectors; conventional solutions involve linear programming or greed...
Marco F. Duarte, Michael B. Wakin, Richard G. Bara...
71
Voted
ICASSP
2008
IEEE
15 years 4 months ago
Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis
Corpus-based concatenative speech synthesis is very popular these days due to its highly natural speech quality. The amount of computation required in the run time, however, is of...
Shinichi Sakai, Tatsuya Kawahara, Shun Nakamura
ICASSP
2008
IEEE
15 years 4 months ago
Subspace compressive detection for sparse signals
The emerging theory of compressed sensing (CS) provides a universal signal detection approach for sparse signals at sub-Nyquist sampling rates. A small number of random projection...
Zhongmin Wang, Gonzalo R. Arce, Brian M. Sadler
ICASSP
2008
IEEE
15 years 4 months ago
Maximum conditional likelihood linear regression and maximum a posteriori for hidden conditional random fields speaker adaptatio
This paper shows how to improve Hidden Conditional Random Fields (HCRFs) for phone classification by applying various speaker adaptation techniques. These include Maximum A Poste...
Yun-Hsuan Sung, Constantinos Boulis, Daniel Jurafs...