PHONE DELETION MODELING IN SPEECH RECOGNITION

MPhil Thesis Defence


Title: "PHONE DELETION MODELING IN SPEECH RECOGNITION"

By

Mr. Yu-Ting Ko


Abstract

In a paper published by Greenberg in 1998, it was said that in conversational 
speech, phone deletion rate may go as high as 12%. On the other hand, Jurafsky 
reported in 2001 that phone deletions cannot be modeled well by traditional 
triphone training. These findings motivate us to model phone deletions 
explicitly in current ASR systems. In this thesis, phone deletions are modeled 
by adding skip arcs to the acoustic units. In order to cope with the 
limitations of using whole words models, context-dependent fragmented word 
models(CD-FWMs) are proposed. Our proposed method is evaluated on both read 
speech (Wall Street Journal) and conversational speech (SVitchboard) task. In 
the read speech evaluation, we obtained a word error rate reduction of about 
11%. Although the improvement in conversational speech is modest, reasons are 
given and relevant analyses are carried out.


Date:			Wednesday, 18 August 2010

Time:			10:00am – 12:00noon

Venue:			Room 3501
 			Lifts 25/26

Committee Members:	Prof. Brian Mak (Supervisor)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Prof. Tan Lee (CUHK)


**** ALL are Welcome ****