Open Access Open Access  Restricted Access Subscription or Fee Access

HMM (Hidden Markov Model) based Speech to Text Conversion for Regional Language (TAMIL)

K. Sweta, B. Amutha

Abstract


The conversion of speech to text for the regional language, TAMIL is being done using HMM (Hidden Markov Model). As the speech to text conversion is yet to be exploited in Tamil language, the purpose of converting speech to text for Tamil language becomes essential. Tamil is a highly inflectional language. The primary aim of this research is to understand the Tamil spoken word and convert it into Tamil text. The full-fledged conversion of all Tamil words through speech to text may be performed in the near future. In the first trial, only 25 familiar Tamil words have been identified, recognized through English, converted and displayed in Tamil text. This conversion of speech to text is done with the help of HMM (Hidden Markov Model) process for 25 Tamil words and the accuracy of conversion is found to be 83%.

Keywords


HMM, Speech to Text Conversion, VAD, Markov Process, Azhagi.

Full Text:

PDF

References


http://en,wikipedia.org/wiki/Tamil_language.

http://en.wikipedia.org/wiki/Tamil_script.

http://jedik.phy.bme.hu/gerjanos/HMM/node4.html.

R. Jagadeesh Kannan, et al ,“An Improved Handwritten Tamil Character Recognition System using Octal graph”. Journal of Computer Science 4 (7): 509-516, 2008,ISSN 1549-3636, 2008 Science Publications.

Kohilavani, et al Automatic Tamil Content Recognition”, international conference on intelligent agent and multi agent system, IAMA, Chennai 2009.

S. Saraswathi, “Improvement in performance of Tamil Phoneme Recognition using Variable length and hybrid language models”, IEEE - ICSCN 2007, MIT Campus, Anna University, Chennai, India. Feb. 22-24, 2007.

S. Saraswathi, et al,“Two level language model for improving the performance of Tamil Speech Recognition”, International Conference on Computational Intelligence and Multimedia Applications 2007.

A.Rathinavelu, et al, “Speech Recognition model for Tamil Stops”, proceedings of the World Congress on Engineering 2007 Vol I,WCE 2007, July 2 - 4, 2007, London, U.K.

Santhosh Yuvaraja, et al,“Building a Tamil Voice using HMM segmented labels”, International Institute of Information Technology, Hyderabad, India Language Technologies Institute, Carnegie Mellon University, USA, communication 2010, national conference on january.

Ralph Niels, et al, “Dynamic time wrapping applied to Tamil Character Recognition”, International Conference on Document Analysis and Recognition,ICDAR, 2005

Zhihong Hu, et al, “Speech recognition using Syllable-Like units”, Center for Spoken Language Understanding,Oregon Graduate Institute of Science and Technology, spoken language, ICSLP 96. Proceedings., fourth international conference on October 1996.

Tomohiro IWASAKI et al, “A real time speaker-independent continuous speech recognition system”, 11th IAPR international conference on Image speech and signal analysis, Netherlands, 1992.

KAI-FU LEE, “Context dependent phonetic Hidden Markov Models for Speaker Independent Continuous Speech Recognition”, IEEE Transactions on Acoustic Speech and Signal Processing, 4 April,1990.

Mei Yuh Hwan, “Shared distribution Hidden Markov Models for Speech recognition”, IEEE Transactions on Speech and Audio Processing, October, 1993.

Cristhian Manuel Durán Acevedo et al, “Integrated System Approach for the Automatic Speech Recognition using Linear predict Coding and Neural Networks”, IEEE, Fourth congress of Electronics, Robotics and automotive Mechanics, 2007.

Mohamed M. Azmi et at, “Syllable-Based Automatic Arabic Speech Recognition in Noisy Enviroment”, Audio Language and Image Processing, 2008. ICALIP 2008, International conference, July 2008.

Mohamed M. Azmi et at, “Noise robustness using different Acoustic units”, Audio Language and Image Processing, 2008. ICALIP 2008, International conference, July 2008.

R.Ramanathan et al, “Optical Character Recognition for English and Tamil Using Support Vector Machines”, Advances in Computing, Control, & Telecommunication technologies, 2009, ACT ’09, International Conference, December 2009.

Junichi Yamagishi et al, “Thousands of Voices for HMM-Based Speech Synthesis–Analysis and Application of TTS Systems Built on Various ASR Corpora”, Audio, Speech and Language Processing, IEEE Transaction, July 2010.

http://en.softonic.com/s/wavepad-voice-recorder.

http://www.azhagi.com/

http://azhagi.com/help/azpowerautotransliteration.html

http://www.w3schools.com/HTML/html_links.asp


Refbacks

  • There are currently no refbacks.