Universiti Teknologi Malaysia Institutional Repository

Speaker recognition based on Hidden Markov Model

Shaikh Salleh, Sheikh Hussain and Sha'arneri, Ahmad Zuri and Yusoff, Zulkamain and AI-Attas, Syed Abdul Rahman and Lim, Soon Chieh and Abdul Rahman, Ahmad Idil and Mat Tahir, Shahirina (2000) Speaker recognition based on Hidden Markov Model. In: Natiaonal Conference on Telecommunication Technology 2000, 20th - 21st Nov. 2000, Hyatt Regency Hotel, Johor Bahru.

PDF - Published Version


In this paper, a method for implementing speaker recognition system using the discrete Hidden Markov Model. This method uses a statistical approach in characterizing speech. The speech utterance is fit into a probabilistic framework, which consist of transition of states and discrete observable sequences. The system is then applied to recognition of isolated Bahasa Melayu digits, that is 'kosong', 'satu', 'dua', 'tiga', 'empat', 'lima', 'enam', 'tujuh', 'lapan', and ┬Ěsembilan'. Experiments were done to evaluate the system's perfomance on speaker recognition. which can be further divided into speaker identification and speaker verification. Speaker recognition, experiments were performed to evaluate the performance of the system with 30 speakers (22 impostors and 8 clients). The identification error was 2%, the false acceptance rate was 28% and the false rejection rate was 1%.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Towards Global Convergence Through Telecommunication
Uncontrolled Keywords:speaker recognition system, Hidden Markov Model
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:10995
Deposited By: Zalinda Shuratman
Deposited On:19 Nov 2010 02:32
Last Modified:19 Nov 2010 02:34

Repository Staff Only: item control page