Sciweavers

82 search results - page 2 / 17
» PAC-Bayesian approach for minimization of phoneme error rate
Sort
View
ACL
2008
13 years 7 months ago
Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion
We present the first English syllabification system to improve the accuracy of letter-tophoneme conversion. We propose a novel discriminative approach to automatic syllabification...
Susan Bartlett, Grzegorz Kondrak, Colin Cherry
INTERSPEECH
2010
13 years 9 days ago
Learning a language model from continuous speech
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
ICASSP
2011
IEEE
12 years 9 months ago
Localization of non-linguistic events in spontaneous speech by Non-Negative Matrix Factorization and Long Short-Term Memory
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detect...
Felix Weninger, Björn Schuller, Martin Wö...
PR
2010
147views more  PR 2010»
13 years 3 months ago
Minimum classification error learning for sequential data in the wavelet domain
Wavelet analysis has found widespread use in signal processing and many classification tasks. Nevertheless, its use in dynamic pattern recognition have been much more restricted ...
D. Tomassi, Diego H. Milone, L. Forzani
DCC
2004
IEEE
14 years 5 months ago
Rate-Distortion Optimized Slicing, Packetization and Coding for Error Resilient Video Transmission
This paper presents an algorithm to optimize the tradeoff between rate and expected end-to-end distortion of a video sequence transmitted over a packet network. The approach optim...
Enrico Masala, Hua Yang, Kenneth Rose, Juan Carlos...