This paper describes in detail the development of the HTK Broadcast News (BN)
transcription system and presents full evaluation results from the 1996, 1997 and 1998 …

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 …

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 …

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 …

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 …

摘要本篇論文提出一個新方法來辨識人臉, 由於在人臉辨識研究當中, 比較難以克服的問題是人
臉影像變化太急劇, 這樣的問題在一般的辨識方法上都不會有太高的辨識率 …