12753 search results - page 2263 / 2551 » is 2002 |
120
click to vote
TASLP
2002
15 years 4 months ago
2002
Large vocabulary continuous speech recognition (LVCSR) systems traditionally represent words in terms of smaller subword units. Both during training and during recognition, they re...
125
click to vote
TASLP
2002
15 years 4 months ago
2002
Two approaches are proposed for the design of tied-mixture hidden Markov models (TMHMM). One approach improves parameter sharing via partial tying of TMHMM states. To facilitate ty...
125
click to vote
TASLP
2002
15 years 4 months ago
2002
The first stage in many pattern recognition tasks is to generate a good set of features from the observed data. Usually, only a single feature space is used. However, in some compl...
146
click to vote
TASLP
2002
15 years 4 months ago
2002
This paper presents a framework for maximum a posteriori (MAP) speaker adaptation of state duration distributions in hidden Markov models (HMM). Four key issues of MAP estimation, ...
139
click to vote
TASLP
2002
15 years 4 months ago
2002
Perceptual audio coders use an estimated masked threshold for the determination of the maximum permissible just-inaudible noise level introduced by quantization. This estimate is d...