9 search results - page 1 / 2 » Advances in Missing Feature Techniques for Robust Large-Voca... |
TASLP
2011
12 years 11 months ago
2011
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...
INTERSPEECH
2010
12 years 11 months ago
2010
Over the years, the focus in noise robust speech recognition has shifted from noise robust features to model based techniques such as parallel model combination and uncertainty de...
ICASSP
2010
IEEE
12 years 11 months ago
2010
IEEE
This paper proposes a method to optimize Viterbi beam search based on search error risk minimization in large vocabulary continuous speech recognition (LVCSR). Most speech recogni...
SIGIR
2009
ACM
13 years 11 months ago
2009
ACM
Well tuned Large-Vocabulary Continuous Speech Recognition (LVCSR) has been shown to generally be more effective than vocabulary-independent techniques for ranked retrieval of spo...