Sciweavers

Share
ICASSP
2009
IEEE

Using collective information in semi-supervised learning for speech recognition

10 years 4 months ago
Using collective information in semi-supervised learning for speech recognition
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learning algorithm for automatic speech recognition. The algorithm determines whether a hypothesized transcription should be used in the training by taking into consideration collective information from all utterances available instead of solely based on the confidence from that utterance itself. It estimates the expected entropy reduction each utterance and transcription pair may cause to the whole unlabeled dataset and choose the ones with the positive gains. We compare our algorithm with existing confidence-based semi-supervised learning algorithm and show that the former can consistently outperform the latter when the same amount of utterances is selected into the training set. We also indicate that our algorithm may determine the cutoff-point in a principled way by demonstrating that the point it finds is ...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICASSP
Authors Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex Acero
Comments (0)
books