Sciweavers

Share
ICASSP
2011
IEEE

MLP based phoneme detectors for Automatic Speech Recognition

9 years 6 months ago
MLP based phoneme detectors for Automatic Speech Recognition
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we explore a different application of these posteriors - as phonetic event detectors for speech recognition. We show how these detectors can be built to reliably capture phonetic events in the acoustic signal by integrating both acoustic and phonetic information about sound classes. These event detectors are used along with Segmental Conditional Random Fields (SCRFs) to improve the performance of speech recognition systems on the Broadcast News task.
Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hyn
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hynek Hermansky
Comments (0)
books