334 search results - page 6 / 67 » Improving speech playback using time-compression and speech ... |
DAGM
2003
Springer
14 years 1 months ago
2003
Springer
In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available. The acoustic models can be improved by interpo...
NAACL
2010
13 years 6 months ago
2010
For extractive meeting summarization, previous studies have shown performance degradation when using speech recognition transcripts because of the relatively high speech recogniti...
ACL
2012
11 years 11 months ago
2012
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...
ICASSP
2011
IEEE
13 years 5 days ago
2011
IEEE
We propose Cross-Channel Spectral Subtraction (CCSS), a source separation method for recognizing meeting speech where one microphone is prepared for each speaker. The method quick...
SPEECH
2011
13 years 3 months ago
2011
This paper first introduces a newly-recorded high quality Romanian speech corpus designed for speech synthesis, called “RSS”, along with Romanian front-end text processing mo...