In this thesis I advocate a probabilistic view of robust speech recognition. I discuss the classification of distorted features using an optimal classifier, and I show how the generation …
C Mathis, T Breuel - 2002 International Conference on Pattern …, 2002 - ieeexplore.ieee.org
A key problem faced by classifiers is coping with styles not represented in the training set. We present an application of hierarchical Bayesian methods to the problem of recognizing …
(57) ABSTRACT A method of performing Speaker adaptation of acoustic models in a band- quantized speech recognition System, wherein the System including one or more acoustic …
A Sankar, VRR Gadde, A Stolcke, F Weng - Speech Communication, 2002 - Elsevier
Over the last few years, the DARPA-sponsored Hub-4 continuous speech recognition evaluations have advanced speech recognition technology for automatic transcription of …
This paper investigates the cross-task recognition and adaptation performance of HMMs trained using either conventional maximum likelihood estimation or the discriminative …
In this paper we describe system architectures for robust MLLR based environmental adaptation of continuous speech recognition systems. Inspired by an existing broadcast …
R Prasad, L Nguyen, R Schwartz… - … Conference on Spoken …, 2002 - isca-archive.org
In this paper we describe our on-going effort in developing a speech recognition system for transcribing courtroom hearings. Court hearings are a rich source of naturally occurring …
摘要(英) Speaker adaptation has been applied to speech recognition to get a speaker dependent system with a good performance. Most adaptation techniques use the initial …