In this study, we have examined the acoustic characteristics of whispered speech and
addressed some of the issues involved in recognition of whispered speech used for …

This paper discusses the Cambridge University HTK (CU-HTK) system for the automatic
transcription of conversational telephone speech. A detailed discussion of the most …

To achieve an optimal word error rate (WER) a speech recognition system has to be
completely adapted to the individual user. While this can be done very effectively by training …

This thesis deals with linear transformations at various stages of the automatic speech
recognition process. In current state-of-the-art speech recognition systems linear …

The tremendous advances in all fields of technology in the twentieth century and especially
advances in the computer technologies in the last 20 years permitted computers to …

This paper deals with the problem of efficient speaker adaptation in large vocabulary
continuous speech recognition (LVCSR) systems. The main goal is to adapt acoustic models …

Automatic speech recognition along with speaker recognition and text to speech conversion
is a fundamental task in speech processing. Natural speech recognition is a difficult and …

In this paper we explore several options for cross-task adaptation in speech recognition and
compare them to develop the new system from scratch. We compare cross-task MAP and …

Improving the performance of the state-of-the-art Mandarin speech recognition system for
non-native speech remains a challenging task because of wide varieties of non-native …

In this work two different approaches for speaker identification are presented. Both systems
are evaluated and compared on subsets of the WSJ database [1] containing 10 native (SI ET …