Data-driven Arabic phoneme recognition using varying number of HMM states

Author

Nahar, K.M.O. ; Al-Khatib, W.G. ; Elshafei, M. ; Al-Muhtaseb, H. ; Alghamdi, M.M.

Author_Institution

Comput. Eng. Dept., King Fahd Univ. Of Pet. & Miner., Dhahran, Saudi Arabia

fYear

2013

Firstpage

1

Lastpage

6

Abstract

Continuous Arabic Speech Recognition, appears in many real life applications. Its speed, accuracy and improvement are highly dependent on the accuracy of the language phonemes set. The main goal of this research is to recognize and transcribe the Arabic phonemes based on a data-driven approach. We built a phoneme recognizer based on a data driven approach using HTK tool. Different numbers of Gaussian mixtures with different numbers of HMM states were used in modeling the Arabic phonemes in order to reach the best configuration. The corpus used consists of about 4000 files, representing 5 recorded hours of modern standard Arabic of TV-News. The maximum phoneme recognition accuracy reached was 56.79%. This result is very encouraging and shows the viability of our approach as compared to using a fixed number of HMM states.

Keywords

Gaussian processes; hidden Markov models; natural language processing; speech processing; speech recognition; television broadcasting; Gaussian mixtures; HMM state varying number; HTK tool; TV-news; continuous Arabic speech recognition; data-driven Arabic phoneme recognition; hidden Markov model; language phonemes set; maximum phoneme recognition accuracy; phoneme recognizer; Accuracy; Dictionaries; Grammar; Hidden Markov models; Speech recognition; Training; Vectors; Arabic Speech Recognition; KFUPM Arabic speech; Phoneme recognition; corpus HMM;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Signal Processing, and their Applications (ICCSPA), 2013 1st International Conference on

Conference_Location

Sharjah

Print_ISBN

978-1-4673-2820-3

Type

conf

DOI

10.1109/ICCSPA.2013.6487258

Filename

6487258