ISOLATED MALAY SPEECH RECOGNITION USING HIDDEN MARKOV MODELS

Rosdi, Fadhilah (2008) ISOLATED MALAY SPEECH RECOGNITION USING HIDDEN MARKOV MODELS. Masters thesis, University of Malaya.

[img] PDF
FADHILAH ROSDI.pdf

Download (1MB)

Abstract

Research in automatic speech recognition by machine has been done for almost four decades. Over the past decades, the development of speech recognition applications gives invaluable contributions to this field of research and becoming mature day by day. In fact, speech has the potential to be a better interface than other computing devices used such as keyboard or mouse. This dissertation aims to develop an automated isolated word speech recognition for Malay language. The study relies heavily on the well known and widely used statistical method in characterizing the speech pattern, the Hidden Markov Model (HMM). Here, we take advantage of HMM which provides a highly reliable way for recognizing speech. This study discusses the theory of HMM and then extends the ideas to the development and implementation by applying this method in computational speech recognition. Basically, the system is able to recognize the spoken utterances in Malay language, by translating the speech waveform into a set of feature vectors, which estimates the observation likelihood by using the Forward algorithm. The HMM parameters are estimated by applying the Baum Welch algorithm on previously trained samples. The most likely sequence is then decoded using Viterbi algorithm, thus producing the recognized word. This research focuses on isolated 5 letters word structure such as empat, lapan, rekod, tidak, tujuh and tutup. The system is relatively successful where it can identify spoken word at 88% recognition rate which is an acceptable rate of accuracy for speech recognition.

Item Type: Thesis (Masters)
Subjects: Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Depositing User: MS NOOR ZAKIRA ZULRIMI
Date Deposited: 12 Jul 2013 07:05
Last Modified: 12 Jul 2013 07:05
URI: http://repository.um.edu.my/id/eprint/282

Actions (login required)

View Item View Item