Sciweavers

Share
ICASSP
2008
IEEE

Polyphase speech recognition

10 years 2 months ago
Polyphase speech recognition
We propose a model for speech recognition that consists of multiple semi-synchronized recognizers operating on a polyphase decomposition of standard speech features. Specifically, we consider multiple out-of-phase downsampled speech features as separate streams which are modeled separately at the lowest level, and are then integrated at the higher level (words) during first-pass decoding. Our model lessens the severity of the oversampling problem in many speech recognition systems – i.e., that speech modulation energy is most important below 25Hz but a 100Hz frame rate gives a modulation bandwidth of 50Hz. Our polyphase approach moreover captures wider and more diverse dynamics within the speech signal. Our integrative network is high-level, namely it couples together and decodes word strings from different recognizers simultaneously and asynchronously. We provide preliminary results on the 10-word vocabulary version of the SVitchboard (small-vocabulary switchboard) task and show ...
Hui Lin, Jeff Bilmes
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICASSP
Authors Hui Lin, Jeff Bilmes
Comments (0)
books