Including uncertainty of speech observations in robust speech recognition

Abstract

Noise compensation methods for speech recognition provide a cleaned version of the speech representation. Usually this cleaned version is the expected value of the speech parameters given the observed noisy speech and the noise statistic. A more realistic representation should include the probability distribution of the cleaned speech instead of its… (More)

Topics

7 Figures and Tables

Statistics

01020201520162017
Citations per Year

Citation Velocity: 6

Averaging 6 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Segura2004IncludingUO, title={Including uncertainty of speech observations in robust speech recognition}, author={Jos{\'e} C. Segura and {\'A}ngel de la Torre and Javier Ram{\'i}rez and Antonio J. Rubio and M. Carmen Ben{\'i}tez}, booktitle={INTERSPEECH}, year={2004} }