46 search results - page 1 / 10 » Recognition Performance of a Structured Language Model |
105
click to vote
ICASSP
2008
IEEE
15 years 7 months ago
2008
IEEE
Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has p...
104
click to vote
ICASSP
2008
IEEE
15 years 7 months ago
2008
IEEE
We propose novel approaches for optimizing the detection performance in spoken language recognition. Two objective functions are designed to directly relate model parameters to tw...
ICASSP
2009
IEEE
15 years 8 months ago
2009
IEEE
We study key issues related to multilingual acoustic modeling for automatic speech recognition (ASR) through a series of large-scale ASR experiments. Our study explores shared str...
159
click to vote
ICASSP
2011
IEEE
14 years 5 months ago
2011
IEEE
This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
109
click to vote
ICASSP
2009
IEEE
15 years 8 months ago
2009
IEEE
We address multistream sign language recognition and focus on efficient multistream integration schemes. Alternative approaches are investigated and the application of Product-HM...