Sciweavers

Share
ICASSP
2011
IEEE

Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling

8 years 6 days ago
Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling
In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling interacts with the risk at a higher level, which is more relevant to the most used evaluation measures, e.g., word error rate(WER). To be specific, the non-uniform error cost is first derived at the word level to minimize the risk w.r.t. WER and then computed on the word lattice using the forwardbackward algorithm. With the statistics obtained from the forwardbackward algorithm, the competing hypotheses for each label word are searched by performing dynamic programming between the label word sequence and the word lattice at the phone level. In order to alleviate the level inconsistency between the acoustic model(phone level) and the evaluation measure(word level), the derived error cost is embedded into the overall objective function in a cross-level fashion. Experiments on a large vocabulary task WSJ0 demon...
Chao Weng, Biing-Hwang Juang
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Chao Weng, Biing-Hwang Juang
Comments (0)
books