Abstract
This paper describes a new technique of language modeling for a highly inflectional Dravidian language, Tamil. It aims to alleviate the main problems encountered in processing of Tamil language, like enormous vocabulary growth caused by the large number of different forms derived from one word. The size of the vocabulary was reduced by, decomposing the words into stems and endings and storing these sub word units (morphemes) in the vocabulary separately. A enhanced morpheme-based language model was designed for the inflectional language Tamil. The enhanced morpheme-based language model was trained on the decomposed corpus. The perplexity and Word Error Rate (WER) were obtained to check the efficiency of the model for Tamil speech recognition system. The results were compared with word-based bigram and trigram language models, distance based language model, dependency based language model and class based language model. From the results it was analyzed that the enhanced morpheme-based trigram model with Katz back-off smoothing effect improved the performance of the Tamil speech recognition system when compared to the word-based language models.
- Ali, A.M.A. 1998. Segmentation and Categorization of Phonemes in Continuous Speech. Technical Report TRCST25JUL98, Center for Sensor Technology, University of Pennsylvania.Google Scholar
- Ali, A.M.A., Vander Spiegel, J., Mueller, P., Haentjens, G., and Berman, J. 1999. An Acoustic-Phonetic feature based system for Automatic Phoneme Recognition in Continuous Speech. In IEEE Proceedings of the International Symposium on Circuits and Systems (ISCAS), 3, 118--121.Google Scholar
- ALI, A.M.A. 2001. Acoustic--Phonetic Features for the Automatic Classification of Stop Consonants. IEEE Trans. Speech and Audio Processing, 9(8), 833--841.Google Scholar
- Anandan, P., Geetha, T.V., and Paratasarathy, R. 2001. Morphological Generator for Tamil. In Proceedings of the Tamil Inayam Conference, Malaysia, 46--54.Google Scholar
- Anandan, P., Saravanan, K., Partasarathi, R., and Geetha, T.V. 2002. Morphological Analyzer for Tamil. In Proceedings of ICON2002, 3--10.Google Scholar
- Arden, A.H. Rev. and Clayton, A. C. 1969. A Progressive Grammar of the Tamil Language, Christian Literature Society, Madras.Google Scholar
- Aversano, G., Esposito, A., Esposito, A., and Marinaro, M. 2001. A new Text Independent Method for Phoneme Segmentation. In Proceedings of IEEE International Workshop on Circuits and Systems, 2, 516--519.Google Scholar
- Aversano, G., Esposito, A., and Chollet, G., 2003. A JAVA interface for speech analysis and segmentation. In Proceedings of the ISCA tutorial and Research Workshop on Non-linear Speech Processing (NOLISP-03), Le Croisic , France, Paper. 026.Google Scholar
- Brown, P., Pietra, S., Della Pietra, V., and Mercer, R. 1993. The mathematics of statistical machine translation: Parameter estimation', Computational Linguistics, 19(2), 263--311. Google Scholar
- Byrne, W., Hacic, J., Iircing, P., Jelinek, F., Khudanpur, S., Krbec,.P., and Psutka, J. 2001. On large vocabulary continuous speech recognition of highly inflectional language -- Czech. In Proceedings of Eurospeech 2001, Aalborg, Denmark, 487--489.Google Scholar
- Choudhury, M. 2003. Rule based grapheme to phoneme mapping for Hindi speech synthesis, presented in 90th Indian Science Congress of ISCA, Bangalore (http://www.mla.iitkgp.ernet.in/papers/G2Phindi.pdf. )Google Scholar
- Collin, M. J. 1996. A new statistical parser based on lexical dependencies. In Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics, 184--191. Google Scholar
- Creutz, M., and Lagus, K. 2002. Unsupervised discovery of Morphemes. In Proceedings of workshop on Morphological and Phonological Learning of ACL 2002, 21--30. Google Scholar
- Franz, M., and Mccarley, S. 2002. Arabic information retrieval at IBM, In Proceedings of TREC 2002, 402--405.Google Scholar
- Gao, J., and Suzuki, H. 2003. Unsupervised learning of dependency structure for language modeling. In Proceedings of ACL-2003, 7--12. Google Scholar
- Huckvale, M., and Fang, A. C. 2002. Using phonologically constrained Morphological Analysis in Speech Recognition. Computer Speech and Language, 165-181.Google Scholar
- Kneissler, J., and Klakow, D. 2001. Speech recognition for huge vocabularies by using optimized sub-word units. In Proceedings of Eurospeech 2001, 69--72.Google Scholar
- Lafferty, J., Sleator , D., and Temperley, D., 1992. Grammatical Trigrams: A probabilistic model of link grammars, In Proceedings of AAAI Fall Symposium on Probabilistic Approaches to Natural LanguagI Issued as technical report CMU-CS-92-181.Google Scholar
- Lafferty, S. and Suhm, B. 1995. Cluster Expansion and Iterative scaling of Maximum Entropy Language Models. In Hanson, K., Silver, R. (Eds) Maximum Entropy and Bayesian Methods, Kluwer Academic Publishers, Norwell, MA.Google Scholar
- Roark B. 2001. Probabilistic top-down parsing and language modeling. Computational Linguistics, 27(2), 249--285. Google Scholar
- Saraswathi, S., and Geetha, T.V. 2004. Building language models for Tamil speech recognition system. In Proceedings of AACC2004 and LNCS3285, 161--168.Google Scholar
- Saraswathi, S., Geetha T.V., and Saravanan, K. 2006a. Integrating language independent segmentation and language dependent phoneme based modeling for Tamil Speech Recognition. Asian J. Information Technology, 5(1), 38--43.Google Scholar
- Saraswathi S., Rajeswari, S., and Geetha T.V. 2006b. Tamil Phoneme segmentation by combining spectral and temporal features. In Proceedingsof the Frontiers of Research on Speech and Music (FRSM-2006). 54--57.Google Scholar
- Smaili , K., Brun A., Zitouni, I., and Haton, J.P. 1999. Automatic and manual clustering for large vocabulary speech recognition - A comparative study. In Proceedings of 6th European Conference on Speech Communication and Technology, 1795--1798.Google Scholar
- Souto, N., Meinedo, H., and Neto, J. 2002. Building Language Models for Continuous Speech Recognition Systems. In Proceedings of Portugal for Natural Language Processing (PorTAL), 101--110. Google Scholar
- Sun, J., Gao, J., Zhang, L., Zhou, M., and Huang, C. 2002. Chinese named entity identification using class based language model, In Proceedings of the 19th International Conf. on Computational Linguistics, 1, 1--7. Google Scholar
- Siivola, V., Hirsimaki, T., Creutz, M., and Kurimo, M., 2003. Unlimited Vocabulary speech recognition based on morphs discovered in an unsupervised manner. In Proc. Eurospeech 2003, 2293--2296.Google Scholar
- Wu, J., and Zheng, F. 2000. On Enhancing Katz smoothing Based on Back-off Language Model. In Proceedings of the International Conference on Speech and Language Processing (ICSLP'2000), 1, 198--201.Google Scholar
- Xu, P., Chelba, C., and Jelinek, F. 2002. A study on richer syntactic dependencies for structured language modeling. In Proceedings of ACL,191--198. Google Scholar
- Xuedong, H., Acero, A., and Hon, H.-W. 2001. Spoken Language Processing, Prentice Hall Publication.Google Scholar
Index Terms
- Comparison of performance of enhanced morpheme-based language model with different word-based language models for improving the performance of Tamil speech recognition system
Recommendations
Topic-Dependent Language Model with Voting on Noun History
Language models (LMs) are an important field of study in automatic speech recognition (ASR) systems. LM helps acoustic models find the corresponding word sequence of a given speech signal. Without it, ASR systems would not understand the language and it ...
Morpheme Based Language Models for Speech Recognition of Czech
TDS '00: Proceedings of the Third International Workshop on Text, Speech and DialogueIn our paper we propose new technique for language modelling of highly inflectional languages such as Czech, Russian an other Slavic languages. Our aim is to alleviate main problem encountered in these languages, which is enormous vocabulary growth ...
Multi class-based n-gram language model for new words using web data
ROCOM'11/MUSP'11: Proceedings of the 11th WSEAS international conference on robotics, control and manufacturing technology, and 11th WSEAS international conference on Multimedia systems & signal processingOut-of-vocabulary (OOV) words cause a serious problem for automatic speech recognition (ASR) system. Not only it will be miss-recognized as an in-vocabulary word with similar phonetics, but the error will also affect nearby words to make errors. ...
Comments