457 search results - page 15 / 92 » Universal background model based speech recognition |
120
click to vote
INTERSPEECH
2010
15 years 4 days ago
2010
Neural network language models (NNLM) have become an increasingly popular choice for large vocabulary continuous speech recognition (LVCSR) tasks, due to their inherent generalisa...
115
click to vote
EMNLP
2006
15 years 6 months ago
2006
This paper presents a corrective model for speech recognition of inflected languages. The model, based on a discriminative framework, incorporates word ngrams features as well as ...
176
Voted
ICASSP
2011
IEEE
14 years 9 months ago
2011
IEEE
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic speech recognition (ASR). There are many well known approaches to subspace based...
156
Voted
INTERSPEECH
2010
15 years 4 days 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...
155
Voted
ICASSP
2009
IEEE
16 years 2 days ago
2009
IEEE
A conventional automatic speech recognizer does not perform well in the presence of noise, while human listeners are able to segregate and recognize speech in noisy conditions. We...