2 search results - page 1 / 1 » Language model transformation applied to lightly supervised ... |
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
For effective training of acoustic and language models for spontaneous speech such as meetings, it is significant to exploit the texts available in a large scale, which may not b...
INTERSPEECH
2010
12 years 12 months ago
2010
Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...