Speaker recognition based on Hidden Markov Model

Abstract

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 ·sembilan'. 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%.