190 search results - page 4 / 38 » Data pruning for template-based automatic speech recognition |
NIPS
1996
14 years 4 days ago
1996
We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of s...
LREC
2008
14 years 8 days ago
2008
In this paper we describe an approach that both creates crosslingual acoustic monophone model sets for speech recognition tasks and objectively predicts their performance without ...
CSL
2007
Springer
13 years 10 months ago
2007
Springer
Automatic speech recognition (ASR) has reached very high levels of performance in controlled situations. However, the performance degrades significantly when environmental noise ...
INTERSPEECH
2010
13 years 5 months ago
2010
We focus in this paper on the named entity recognition task in spoken data. The proposed approach investigates the use of various contexts of the words to improve recognition. Exp...
ACL
2009
13 years 8 months ago
2009
We demonstrate that transformation-based learning can be used to correct noisy speech recognition transcripts in the lecture domain with an average word error rate reduction of 12...