66 search results - page 4 / 14 » A flat direct model for speech recognition |
PAMI
2002
13 years 5 months ago
2002
The multimodal nature of speech is often ignored in human-computer interaction, but lip deformations and other body motion, such as those of the head, convey additional information...
INTERSPEECH
2010
13 years 18 days ago
2010
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
ICASSP
2010
IEEE
13 years 6 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...
SEMCO
2007
IEEE
14 years 1 days 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...
INTERSPEECH
2010
13 years 18 days ago
2010
In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models fo...