8 search results - page 2 / 2 » Acoustic model training for non-audible murmur recognition u... |
INTERSPEECH
2010
12 years 11 months ago
2010
To achieve natural high quality synthesised speech in HMMbased speech synthesis, the effective modelling of complex acoustic and linguistic contexts is critical. Traditional appro...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
When exposed to environmental noise, speakers adjust their speech production to maintain intelligible communication. This phenomenon, called Lombard effect (LE), is known to consi...
INTERSPEECH
2010
12 years 11 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 "...