14 search results - page 2 / 3 » Improving Children's Speech Recognition by HMM Interpolation... |
IEICET
2008
13 years 4 months ago
2008
In this paper, we propose a PLSA-based language model for sports live speech. This model is implemented in unigram rescaling technique that combines a topic model and an n-gram. I...
CSL
2002
Springer
13 years 4 months ago
2002
Springer
We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for HMM models, context-depend...
ICMCS
2006
IEEE
13 years 10 months ago
2006
IEEE
This paper presents an efficient algorithm for gesture detection in lecture videos by combining visual, speech and electronic slides. Besides accuracy, response time is also cons...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
ICASSP
2010
IEEE
13 years 4 months ago
2010
IEEE
This paper addresses the problem of developing appropriate features for use in direct modeling approaches to speech recognition, such as those based on Maximum Entropy models or S...