Add to ORKGWe previously introduced a new Bayesian predictive classi-fication (BPC) approach to robust speech recognition and showed that BPC is capable of coping with many types of distortions. We also learned that the efficacy of the BPC al-gorithm is inflEenced by the appropriateness of the prior dis-tribution for the mismatch being compensated. If the prior distribution fails to characterize the variability reflected in the model parameters, then the BPC will not help much. In this paper, we show how the knowledge and/or experience of the interaction between speech signal and the possible mis-match guide us to obtain a better prior distribution which improves the performance of the BPC approach. 1. IIVTRODUCTION Most of the current itutomatic spee...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...
We introduce a new decision strategy called Bayesian predictive classification (BPC) for robust spee...
Abstract—In this paper, we study a category of robust speech recognition problem in which mismatches...
recognition problem in which mismatches exist between training and testing conditions, and no accura...
We study a category of robust speech recognition problem in which mismatches exist between training ...
In this paper we present an approach that makes use of both Bayesian predictive classification (BPC)...
This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, ...
This paper proposes a prior distribution determination tech-nique using cross validation for speech ...
©2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish thi...
In this paper, we extend our previously proposed Viterbi Bayesian predictive classification (VBPC) a...
Bayesian approaches to speaker adaptation are popular in Automatic Speech Recognition (ASR) systems....
Abstract—In this paper, we propose a robust compensation strategy to deal effectively with extraneou...
I hereby declare that I am the sole author of this thesis. I authorize the University of Waterloo to...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...
We introduce a new decision strategy called Bayesian predictive classification (BPC) for robust spee...
Abstract—In this paper, we study a category of robust speech recognition problem in which mismatches...
recognition problem in which mismatches exist between training and testing conditions, and no accura...
We study a category of robust speech recognition problem in which mismatches exist between training ...
In this paper we present an approach that makes use of both Bayesian predictive classification (BPC)...
This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, ...
This paper proposes a prior distribution determination tech-nique using cross validation for speech ...
©2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish thi...
In this paper, we extend our previously proposed Viterbi Bayesian predictive classification (VBPC) a...
Bayesian approaches to speaker adaptation are popular in Automatic Speech Recognition (ASR) systems....
Abstract—In this paper, we propose a robust compensation strategy to deal effectively with extraneou...
I hereby declare that I am the sole author of this thesis. I authorize the University of Waterloo to...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...
Speech perception involves prediction, but how is that prediction implemented? In cognitive models p...