1923 search results - page 277 / 385 » Weighted Decision Trees |
169
click to vote
INTERSPEECH
2010
15 years 1 months ago
2010
Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be ident...
203
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
This paper proposes a technique for constructing independent parameter tying structures of mean and variance in HMMbased speech synthesis. Conventionally, mean and variance parame...
142
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
We propose to improve speech recognition performance on speaker-independent, mixed language speech by asymmetric acoustic modeling. Mixed language is either inter-sentential code ...
160
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
We address the problem of pronunciation variation in conversational speech with a context-dependent articulatory featurebased model. The model is an extension of previous work usi...
161
click to vote
CVPR
2004
IEEE
16 years 8 months ago
2004
IEEE
Object recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the...