Morpheme-based automatic speech recognition for a morphologically rich language - Amharic

Out-of-vocabulary (OOV) words are a major source of error in a speech recognition system and various methods have been proposed to increase the performance of the systems by properly dealing with them. This paper presents an automati c speech recognition experiment conducted to see the effect o f OOV words on the performance speech recognition system for Amharic (a morphologically rich language). We tried to solve the OOV problem by using morphemes as dictionary and language model units. It has been found that for a small vocabulary (5k) system morphemes are better lexical and lan guage modeling units than words. An absolute improvement (in word recognition accuracy) of 11.57% has been obtained as a result of using a morph-based vocabulary. However, for large vocabularies morpheme-based systems did not brin g much performance improvement as they suffer from acoustic confusability and limited language model scope while wordbased recognizers benefit much from OOV rate reduction.

[1]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[2]  Tesfaye Bayu.  Automatic Morphological Analyzer for Amharic an Experiment Employing Unsupervised Learning and Autosegmental Analysis Approaches , 2002 .

[3]  Solomon Teferra Abate,et al.  An Amharic speech corpus for large vocabulary continuous speech recognition , 2005, INTERSPEECH.

[4]  E.W.D. Whittaker,et al.  Vocabulary independent speech recognition using particles , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[5]  Philip C. Woodland,et al.  Particle-based language modelling , 2000, INTERSPEECH.

[6]  Petra Geutner,et al.  Using morphology towards better large-vocabulary speech recognition systems , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[7]  Mikko Kurimo,et al.  Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner , 2003, INTERSPEECH.

[8]  Thomas Pellegrini,et al.  Investigating automatic decomposition for ASR in less represented languages , 2006, INTERSPEECH.

[9]  Solomon Teferra Abate,et al.  Morpheme-Based and Factored Language Modeling for Amharic Speech Recognition , 2009, LTC.

[10]  Mikko Kurimo,et al.  Morphologically Motivated Language Models in Speech Recognition , 2005 .

[11]  William J. Byrne,et al.  On large vocabulary continuous speech recognition of highly inflectional language - czech , 2001, INTERSPEECH.

[12]  Mark J. F. Gales,et al.  Recent Progress in Large Vocabulary Continuous Speech Recognition: An HTK Perspective , 2006 .

[13]  Mathias Creutz,et al.  Unsupervised Morpheme Segmentation and Morphology Induction from Text Corpora Using Morfessor 1.0 , 2005 .

[14]  Rainer Voigt,et al.  THE CLASSIFICATION OF CENTRAL SEMITIC , 1987 .

[15]  Tanja Schultz,et al.  Turkish LVCSR: towards better speech recognition for agglutinative languages , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[16]  Thomas Pellegrini,et al.  Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language , 2007, INTERSPEECH.

[17]  P.C. Woodland,et al.  The 1994 HTK large vocabulary speech recognition system , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.