650 search results - page 48 / 130 » Comparative Evaluation of Speech Parameterizations for Speec... |
ICASSP
2009
IEEE
14 years 3 months ago
2009
IEEE
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
SEMCO
2007
IEEE
14 years 3 months ago
2007
IEEE
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
NAACL
1994
13 years 10 months ago
1994
In this paper, we propose a new stochastic language model that integrates local and global constraints effectively and describe a speechrecognition system basedon it. Theproposedl...
INTERSPEECH
2010
13 years 3 months ago
2010
In this paper, we propose a joint optimal method for automatic speech recognition (ASR) and ideal binary mask (IBM) estimation in transformed into the cepstral domain through a ne...
ICASSP
2010
IEEE
13 years 9 months ago
2010
IEEE
In a paper published by Greenberg in 1998, it was said that in conversational speech, phone deletion rate may go as high as 12% whereas syllable deletion rate is about 1%. The fi...