Improvements in recognition of conversational telephone speech
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference（1999）
Abstract
This paper describes recent changes in Dragon's speech recognition system which have markedly improved performance on conversational telephone speech. Key changes include: the conversion to modified perceptual linear prediction (PLP)-based cepstra from mel-cepstra; the replacement of our usual IMELDA transformation by a new transform using “semi-tied covariance”; a new multi-pass adaptation protocol; probabilities on alternate pronunciations in the lexicon; the addition of word-boundary tags in our acoustic models and the redistribution of model parameters to build fewer output distributions but with more mixture components per model
MoreTranslated text
Key words
cepstral analysis,prediction theory,probability,speech recognition,telephony,Dragon speech recognition system,acoustic models,alternate pronunciations probability,conversational telephone speech recognition,lexicon,mixture components,model parameters redistribution,modified PLP-based cepstra,modified perceptual linear prediction,multi-pass adaptation protocol,output distributions,performance improvement,semi-tied covariance,transform,word-boundary tags,
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined