Skip to main content
×
×
Home

Using morphemes in language modeling and automatic speech recognition of Amharic

  • MARTHA YIFIRU TACHBELIE (a1), SOLOMON TEFERRA ABATE (a1) and WOLFGANG MENZEL (a2)
Abstract

This paper presents morpheme-based language models developed for Amharic (a morphologically rich Semitic language) and their application to a speech recognition task. A substantial reduction in the out of vocabulary rate has been observed as a result of using subwords or morphemes. Thus a severe problem of morphologically rich languages has been addressed. Moreover, lower perplexity values have been obtained with morpheme-based language models than with word-based models. However, when comparing the quality based on the probability assigned to the test sets, word-based models seem to fare better. We have studied the utility of morpheme-based language models in speech recognition systems and found that the performance of a relatively small vocabulary (5k) speech recognition system improved significantly as a result of using morphemes as language modeling and dictionary units. However, as the size of the vocabulary increases (20k or more) the morpheme-based systems suffer from acoustic confusability and did not achieve a significant improvement over a word-based system with an equivalent vocabulary size even with the use of higher order (quadrogram) n-gram language models.

Copyright
References
Hide All
Abate, S. T. 2006. Automatic Speech Recognition for Amharic. PhD. thesis. University of Hamburg.
Abate, S. T., Menzel, W., and Tafila, B. 2005. An Amharic speech corpus for large vocabulary continuous speech recognition. In Proceedings of 9th European Conference on Speech Communication and Technology, Interspeech-2005, Lisbon, Portugal, pp. 1601–4.
Adafre, S. F. 2005. Part of speech tagging for Amharic using conditional random fields. In Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, Ann Arbor, Michigan, USA, pp. 4754.
Alemayehu, N., and Willett, P. 2002. Stemming of amharic words for information retrieval. Literary and Linguistic Computing 17 (1): 117.
Amsalu, S., and Gibbon, D. 2005. Finite state morphology of Amharic. In Proceedings of International Conference on Recent Advances in Natural Language Processing, Borovets, Bulgaria, pp. 4751.
Argaw, A. A., and Asker, L. 2007 An amharic stemmer: reducing words to their citation forms. In Proceedings of the Workshop on Computational Approaches to Semitic Languages: Common Issues and Resources - ACL 2007, Prague, Czech Republic, pp. 104–10.
Badr, I., Zbib, R., and Glass, J.. 2008. Segmentation for English-to-Arabic statistical machine translation. In Proceedings of ACL-08, HLT Short Paper, Columbus, Ohio State, pp. 153–6.
Bayou, A. 2000. Developing Automatic Word Parser for Amharic Verbs and their Derivation. Master's thesis, Addis Ababa University.
Bayu, T. 2002. Automatic Morphological Analyzer for Amharic: An Experiment Employing Unsupervised Learning and Autosegmental Analysis Approaches. Master's thesis, Addis Ababa University.
Bender, M., Bowen, J., Cooper, R., and Ferguson, C. 1976. Languages in Ethiopia. London: Oxford University Press.
Bouwman, G., Cranen, B., and Boves, L. 2004. Predicting word correct rate from acoustic and linguistic confusability. In Proceeding the 8th International Conference on Spoken Language Processing, Jeju Island, Korea, pp. 1481–4.
Chen, S. F., and Goodman, J. 1998. An empirical study of smoothing techniques for language modeling. Technical Report TR-10-98, Computer Science Group, Harvard University.
Creutz, M. 2006. Induction of the Morphology of Natural language: Unsupervised Morpheme Segmentation with Application to Automatic Speech Recognition. PhD thesis, Helsinki University of Technology.
Creutz, M., Hirsimäki, T., Kurimo, M., Puurula, A., Pylkkönen, J., Siivola, V., Varjokallio, M., Arisoy, E., Saraçlar, M., and Stolcke, A. 2007. Analysis of morph-based speech recognition and the modeling of out-of-vocabulary words across languages. In Proceedings of NAACL HLT 2007, Rochester, NY, USA, pp. 380–7.
Creutz, M., and Lagus, K. 2005. Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.1. Technical Report A81, Neural Networks Research Center, Helsinki University of Technology.
Creutz, M., and Lind, K. 2004. Morpheme Segmentation Gold Standards for Finnish and English. Technical Report A77, Helsinki University of Technology.
El-Desoky, A., Gollan, C., Rybach, D., Schlüter, R., and Ney, H. 2009. Investigating the use of morphological decomposition and diacritization for improving arabic LVCSR. In Proceedings of INTERSPEECH 2009, Brighton, UK, pp. 2679–82.
Finke, M., Geutner, P., Hild, H., Kemp, T., Ries, K., and Westphal, M. 1997. The Karlsruhe - Verbmobil speech recognition engine. Proceedings of International Conference on Acoustic, Speech, and Signal Processing, ICASSP 1997 1: 83–6.
Fissaha, S., and Haller, J. 2003. Amharic verb lexicon in the context of machine translation. Proceedings of the 10th Conference on Traitement Automatique des Langues Naturelles, Butz-sur-Mer, France, 2: 183–92.
Gasser, M. 2011. Hornmorpho: a system for morphological processing of Amharic, Oromo, and Tigrinya. In Proceedings of the Conference on Human Language Technology for Development - HLTD 2011, Alexandria, Egypt, pp. 94–9.
Geutner, P. 1995. Using morphology towards better large-vocabulary speech recognition systems. Proceedings of IEEE International on Acoustics, Speech and Signal Processing 1: 445–8.
Heintz, I. 2010. Arabic Language Modeling with Stem-derived Morphemes for Automatic Speech Recognition. PhD thesis, Graduate Program in Linguistics, The Ohio State University.
Hirsimäki, T., Creutz, M., Siivola, V., and Kurimo, M. 2005. Morphologically motivated language models in speech recognition. In Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning, Espoo, Finland, pp. 121–6.
Ircing, P., Krebc, P., Hajič, J., Psutka, J., Khudanpur, S., Jelinek, F., and Byrne, W., 2001. On large vocabulary continuous speech recognition of highly inflectional language - Czech. In Proceeding of the European Conference on Speech Communication and Technology, Aalborg, Denmark, pp. 487–9.
Junqua, J. C., and Haton, J. P.. 1996. Robustness in Automatic Speech Recognition: Fundamentals and Applications. London: Kluwer Academic.
Kirchhoff, K., Bilmes, J., Henderson, J., Schwartz, R., Noamany, M., Schone, P., Ji, G., Das, S., Egan, M., He, F., Vergyri, D., Liu, D., and Duta, N. 2002. Novel speech recognition models for Arabic. Technical Report, Johns-Hopkins University Summer Research Workshop.
Labaka, G., Stroppa, N., Way, A., and Sarasola, K. 2007. Comparing rule-based and data-driven approaches to spanish-to-banque machine translation. In Proceedings of Machine Translation Summit XI, 2007, Copenhagen, Denmark.
Manning, C. D., and Schütze, H. 1999. Foundations of Statistical Natural Language Processing. Cambridge and London: The MIT Press.
Oflazer, K. 2008. Statistical machine translation into a morphologically complex language. In Proceedings of the 9th International Conference on Computational Linguistics and Intelligent Text Processing CICLing’08, Haifa, Israel. Published as LNCS vol. 4919, pp. 376–87.
Pellegrini, T., and Lamel, L. 2006. Investigating automatic decomposition for ASR in less represented languages. In Proceedings of INTERSPEECH 2006, Pittsburgh, Pennsylvania, USA, pp. 285–8.
Pellegrini, T., and Lamel, L. 2007. Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language. In Proceedings of INTERSPEECH 2007, pp. 1797–1800.
Pellegrini, T., and Lamel, L. 2009. Automatic word decompounding for ASR in a morpholo- gically rich language: application to amharic. IEEE Transactions on Audio, Speech, and Language Processing 17 (5): 863–73.
Sproat, R. 1992. Morphology and Computation. London: The MIT Press.
Stolcke, A. 2002. SRILM – an extensible language modeling toolkit. Proceedings of International Conference on Spoken Language Processing 2: 901–4.
Tachbelie, M. Y. 2010. Morphology-Based Language Modeling for Amharic. PhD thesis, University of Hamburg. http://www2.sub.uni-hamburg.de/opus/volltexte/2010/4848/pdf/TachbelieDissertation.pdf. Last accessed on the 3rd of December, 2012.
Tachbelie, M. Y., and Menzel, W. 2009. Morpheme-based language modeling for inflectional language – Amharic. In Nicolov, N., Angelova, G., and Mitkov, R. (eds.), Recent Advances in Natural Language Processing V, Current Issues in Linguistic Theory, pp. 301–10. Amsterdam and Philadelphia: John Benjamin's Publishing.
Teferra, A., and Hudson, G. 2007. Essentials of Amharic. Köln: Köppe.
Voigt, R. M. 1987. The classification of central semitic. Journal of Semitic Studies 32: 121.
Vergyri, D., Kirchhoff, K., Duh, K., and Stolcke, A. 2004. Morphology-based language modeling for Arabic speech recognition. In Proceedings of International Conference on Spoken Language Processing, Jeju Island, Korea, pp. 2245–8.
Whittaker, E., and Woodland, P. 2000. Particle-based language modeling. In Proceeding of International Conference on Spoken Language Processing, Beijing, China, pp. 170–3.
Yimam, B. 2007. YäamarIña Säwasäw, 2nd ed.Addis Ababa: EMPDE.
Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., and Woodland, P. 2006. The HTK Book. Cambridge University, Engineering Department. Cambridge, UK.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Natural Language Engineering
  • ISSN: 1351-3249
  • EISSN: 1469-8110
  • URL: /core/journals/natural-language-engineering
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed