376 search results - page 39 / 76 » Analysis-by-synthesis features for speech recognition |
VLSID
2006
IEEE
14 years 10 months ago
2006
IEEE
Advances in Human Computer Interaction(HCI) technology has resulted in widespread development of natural language and speech applications. These applications are known to be compu...
ICASSP
2011
IEEE
13 years 1 months ago
2011
IEEE
We propose to include synchrony effects, known to exist in the auditory system, to represent voiced parts of the speech signal in a robust way. The system decomposes the input sig...
SPEECH
2011
13 years 4 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...
ACL
2012
12 years 2 days 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 1 months ago
2011
IEEE
A novel frame-wise model adaptation approach for reverberationrobust distant-talking speech recognition is proposed. It adjusts the means of static cepstral features to capture th...