29 search results - page 3 / 6 » Detection-based speech recognition with sparse point process... |
ICASSP
2009
IEEE
15 years 4 months ago
2009
IEEE
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 learn...
ICASSP
2009
IEEE
15 years 4 months ago
2009
IEEE
Despite their effectiveness for robust speech processing, missing data techniques are vulnerable to errors in the classification of the input speech signal’s time-frequency poi...
EACL
2006
ACL Anthology
14 years 11 months ago
2006
ACL Anthology
In this paper, we explore statistical language modelling for a speech-enabled MP3 player application by generating a corpus from the interpretation grammar written for the applica...
CIKM
2008
Springer
14 years 11 months ago
2008
Springer
Tagged data is rapidly becoming more available on the World Wide Web. Web sites which populate tagging services offer a good way for Internet users to share their knowledge. An in...
ICASSP
2009
IEEE
15 years 4 months ago
2009
IEEE
Model compensation is a standard way of improving the robustness of speech recognition systems to noise. A number of popular schemes are based on vector Taylor series (vts) compen...