INTERSPEECH 2013 14thAnnual Conference of the International Speech Communication Association Lyon, France August 25-29, 2013

Experiments Towards a Better LVCSR System for Tamil

Melvin Jose Johnson Premkumar (1), Ngoc Thang Vu (2), Tanja Schultz (2)

(1) Anna University, India
(2) KIT, Germany

This paper summarizes our latest efforts in the development of a Large Vocabulary Continuous Speech Recognition (LVCSR) system for Tamil at different levels: pronunciation dictionary, language modeling (LM) and front-end. Usually in Tamil there are not many word-pronunciation pairs to train data-driven grapheme-to-phoneme (G2P) converters. Therefore, we explore the correlation between the amount of training data and the performance of the grapheme-to-phoneme (G2P) conversion. To address the morphological complexity of Tamil, we investigate different levels of morphemes for language modeling including a comparison between our Dictionary Unit Merging Algorithm (DUMA) and Morfessor, followed by various experiments on hybrid systems using word and morpheme LMs. Finally, we integrate our multilingual bottle-neck features framework with Tamil LVCSR. The final best system produced 21.34% Syllable Error Rate (SyllER) on our Tamil test set.

Full Paper

Bibliographic reference.  Premkumar, Melvin Jose Johnson / Vu, Ngoc Thang / Schultz, Tanja (2013): "Experiments towards a better LVCSR system for tamil", In INTERSPEECH-2013, 2202-2206.