Automatic Word Decompounding for ASR in a Morphologically Rich Language: Application to Amharic

IEEE Transactions on Audio, Speech and Language Processing

Volumn 17, Issue 5, 2009, Pages 863-873

  Pellegrini, Thomas ^a   Lamel, Lori ^a  

^a CNRS   (France)

Author keywords

Automatic speech recognition (ASR); broadcast news transcription; less represented languages; lexical modeling; morphologically rich languages (MRLs)

Indexed keywords

EID: 85008009596     PISSN: 15587916     EISSN: 15587924     Source Type: Journal    
DOI: 10.1109/TASL.2009.2022295     Document Type: Article

References (45)

1. J.-L. Gauvain, L. Lamel, G. Adda, and M. Adda-Decker, “Speaker-independent continuous speech dictation,” in Speech Commun., 1994, vol. 15, pp. 21–37.
2. M. Adda-Decker, “A corpus-based decompounding algorithm for German lexical modeling in LVCSR,” in Proc. Euro speech, Geneva, 2003, pp. 257–260.
3. P. Geutner, “Using morphology towars better large-vocabulary speech recognition systems,” in Proc. ICASSP, Detroit, 1995, pp. 445–448.
4. M. Kurimo, A. Puurula, E. Arisoy, V. Siivola, T. Hirsimaki, J. Pylkkonen, T. Alumae, and M. Saraclar, “Unlimited vocabulary speech recognition for agglutinative languages,” in Proc. HLT-NAACL, New York, 2006, pp. 487–494.
5. V.-B. Le, L. Besacier, S. Seng, B. Bigi, and T.-N.-D. Do, “Recent advances in automatic speech recognition for vietnamese,” in Proc. SLTU, Hanoi, Vietman, 2008, pp. 47–52.
6. R. Ordelman, A. van Hessen, and F. de Jong, “Compound decomposition in Dutch large vocabulary speech recognition,” in Proc. Eurospeech, Geneva, 2003, pp. 225–228.
7. M. Creutz and K. Lagus, “Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0,” Computer and Information Science, Report A81, 2005.
8. T. Schultz, A. Black, S. Badaskar, M. Hornyak, and J. Kominek, “SPICE: Web-based tools for rapid language adaptation in speech processing systems,” in Proc. Interspeech, Antwerp, 2007, pp. 2125–2128.
9. S. Abate and W. Menzel, “Automatic speech recognition for an under-resourced language—Amharic,” in Proc. Interspeech, Antwerp, Belgium, 2007, pp. 1541–1544.
10. T. Pellegrini and L. Lamel, “Investigating automatic decomposition for ASR in less represented languages,” in Proc. Interspeech, Pittsburgh, PA, 2006, pp. 285–288.
11. K. Kirchhoff, J. Bilmes, J. Henderson, and R. Schwartz, “Novel speech recognition models for Arabic,” in Johns Hopkins University Summer Research Workshop, 2002, Final report.
12. T. Pellegrini and L. Lamel, “Experimental detection of vowel pronunciation variants in Amharic,” in Proc. LREC, Genoa, Italy, 2006, pp. 1005–1008.
13. R. Jakobson, G. Fant, and M. Halle, Preliminaries to Speech Analysis. Cambridge, MA: MIT Press, 1952.
14. T. Pellegrini and L. Lamel, “Using phonetic features in unsupervised word decompounding for asr with application to a less-represented language,” in Proc. Interspeech, Antwerp, Belgium, 2007, pp. 1797–1800.
15. A. Martinet, Elements de Linguistique Generale. Paris, France: Armand Colin, 1980.
16. G. Adda, M. Adda-Decker, J.-L. Gauvain, and L. Lamel, “Text normalization and speech recognition in French,” in Proc. EuroSpeech, Rhodes, Greece, 1997, vol. 5, pp. 2711–2714.
17. F. Van Eynde and D. Gibbon, Lexicon Development for Speech and Language Processing. Dordrecht, The Netherlands: Kluwer, 2000.
18. M. Finke and A. Waibel, “Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition,” in Proc. Eurospeech, Rhodes, 1997, pp. 1963–1966.
19. J.-L. Gauvain, G. Adda, L. Lamel, and M. Adda-Decker, “Transcribing broadcast news: The Limsi Nov96 Hub4 System,” in Proc. ARPA, Chantilly, France, 1997, pp. 56–63.
20. A. Stolcke, H. Bratt, J. Butzberger, H. Franco, V. G. Rao, M. Plauche, C. Richey, E. Shriberg, K. Sonmez, F. Weng, and J. Zheng, “The SRI March 2000 hub-5 conversational speech transcription system,” in Proc. NIST Speech Transcription Workshop, College Park, MD, 2000.
21. T. Emerson, “The second international chinese word segmentation bakeoff,” in Proc. 4th SIGHAN Workshop Chinese Lang. Process., Jeju, Korea, 2005, pp. 123–133.
22. L. Chen, L. Lamel, and J.-L. Gauvain, “Transcribing mandarin broadcast news,” in Proc. IEEE Workshop Autom. Speech Recognition, St. Thomas, Virgin Islands, 2003, pp. 99–104.
23. M.-Y. Hwang, X. Lei, W. Wang, and T. Shinozaki, “Investigation on Mandarin broadcast news speech recognition,” in Proc. ICSLP, Pittsburgh, PA, 2006, pp. 1233–1236.
24. M. Creutz, T. Hirsimaki, M. Kurimo, A. Puurula, J. Pylkkonen, V. Si-ivola, M. Varjokallio, E. Arisoy, M. Saraclar, and A. Stolcke, “Morph-based speech recognition and modeling of out-of-vocabulary words across languages,” ACM Trans. Speech Lang. Process., vol. 5.1 Article 3, 2007.
25. J.-L. Gauvain, G. Adda, M. Adda-Decker, A. Allauzen, V. Gendner, H. Lamel, and L. Schwenk, “Where are we in transcribing French broadcast news?,” in Proc. Interspeech, Lisbon, Portugal, 2005, pp. 1665–1668.
26. E. Arisoy, H. Sak, and M. Saraclar, “Language modeling for automatic Turkish broadcast news transcription,” in Proc. Interspeech, Antwerp, Belgium, 2007, pp. 2381–2384.
27. E. Arisoy and M. Saraclar, “Lattice extension and vocabulary adaptation for Turkish LVCSR,” Speech Lang. Process., vol. 10, no. 1, 2009.
28. M. Afify, R. Sarikaya, H.-K. Kuo, L. Besacier, and Y. Gao, “On the use of morphological analysis for dialectal Arabic speech recognition,” in Proc. ICSLP, Pittsburgh, PA, 2006, pp. 277–280.
29. B. Xiang, K. Nguyen, L. Nguyen, R. Schwartz, and J. Makhoul, “Morphological decomposition for Arabic broadcast news transcription,” in Proc. ICASSP, Toulouse, France, 2006, vol. I, pp. 1089–1092.
30. L. Lamel, A. Messaoudi, and J.-L. Gauvain, “Investigating morphological decomposition for transcription of Arabic broadcast news and broadcast conversation data,” in Proc. Interspeech, Brisbane, Australia, 2008, pp. 1429–1432.
31. Omniglot, “A guide to the languages, alphabets, syllabaries and other writing systems of the world.” [Online]. Available: http://www.om-niglot.com/
32. L. Asker, A. Argaw, B. Gamback, and M. Sahlgren, “Applying machine learning to Amharic text classification,” in Proc. 5th World Congr. African Linguist., Cologne, Germany, 2007.
33. D. Appleyard, Colloquial Amharic. London, U.K.: Routledge, 1995.
34. K. Kirchhoff and R. Sarikaya, “Processing morphologically rich languages,” in Proc. Workshop Interspeech, Antwerp, Belgium, 2007.
35. P. Geutner, M. Finke, and A. Waibel, “Phonetic-distance-based hypothesis driven lexical adaptation for transcribing multlingual broadcast news,” in Proc. ICSLP, Sydney, Australia, 1998, pp. 771–774.
36. P. Geutner, C. Carki, and T. Schultz, “Turkish LVCSR: Towards better speech recognition for agglutinative languages,” in Proc. ICASSP, Istanbul, Turkey, 2000, pp. 1563–1566.
37. E. Arisoy, H. Dutagaci, and L. Arslan, “A unified language model for large vocabulary continuous speech recognition of Turkish,” Signal Process., vol. 86, no. 10, pp. 2844–2862, 2006.
38. Z. Harris, “From phoneme to morpheme,” in Language, 1955, vol. 31, pp. 190–222.
39. J. Goldsmith, “Unsupervised learning of the morphology of a natural language,” Comput. linguist., vol. 27, no. 2, pp. 153–198, 2001.
40. M. Halle and G. Clements, Problem Book in Phonology. Cambridge, MA: MIT Press, 1983.
41. T. Pellegrini, “Transcription Automatique de Langues peu Dotées” Ph.D., Paris-Sud Univ., Orsay, 2008.
42. S. Abate, W. Menzel, and B. Tafila, “An Amharic speech corpus for large vocabulary continuous speech recognition,” in Proc. Interspeech, Lisbon, Portugal, 2005, pp. 1601–1604.
43. L. Lamel, J.-L. Gauvain, G. Adda, M. Adda-Decker, L. Canseco, L. Chen, O. Galibert, A. Messaoudi, and H. Schwenk, “Speech transcription in multiple languages,” in Proc. ICASSP, Montreal, QC, Canada, 2004, vol. 3, pp. 757–760.
44. J.-L. Gauvain, L. Lamel, and G. Adda, “The LIMSI broadcast news transcription system,” Speech Commun., vol. 37, no. 1–2, pp. 89–108, 2002.
45. D. Yacob, “Application of the double metaphone algorithm to Amharic orthography,” in Proc. Int. Conf. Ethiopian Studies XV, Cologne, Germany, 2003, pp. 1–13.