DMCA
Speech/music Discrimination Based On Posterior Probability Features (1999)
Cached
Download Links
| Citations: | 51 - 9 self |
BibTeX
@MISC{Williams99speech/musicdiscrimination,
author = {Gethin Williams and Daniel P. W. Ellis},
title = {Speech/music Discrimination Based On Posterior Probability Features},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A hybrid connectionist-HMM speech recognizer uses a neural network acoustic classifier. This network estimates the posterior probability that the acoustic feature vectors at the current time step should be labelled as each of around 50 phone classes. We sought to exploit informal observations of the distinctions in this posterior domain between nonspeech audio and speech segments well-modeled by the network. We describe four statistics that successfully capture these differences, and which can be combined to make a reliable speech/nonspeech categorization that is closely related to the likely performance of the speech recognizer. We test these features on a database of speech/music examples, and our results match the previously-reported classification error, based on a variety of special-purpose features, of 1.4% for 2.5 second segments. We also show that recognizing segments ordered according to their resemblance to clean speech can result in an error rate close to the ideal minimum o...
Keyphrases
speech music discrimination posterior probability feature neural network acoustic classifier previously-reported classification error acoustic feature vector reliable speech nonspeech categorization hybrid connectionist-hmm speech recognizer speech recognizer special-purpose feature speech segment second segment likely performance speech music example ideal minimum current time step informal observation phone class error rate close posterior domain nonspeech audio posterior probability
