Using data-driven subword units in language model of highly inflective slovenian language

International Journal of Pattern Recognition and Artificial Intelligence

Volumn 23, Issue 2, 2009, Pages 287-312

  Maučec, Mirjam Sepesy ^a   Rotovnik, Tomaž ^a   Kačič, Zdravko ^a   Brest, Janez ^a  

^a UNIVERSITY OF MARIBOR   (Slovenia)

Author keywords

Inflective language; Speech recognition; Statistical language modeling; Subword units

Indexed keywords

COMPLEX MORPHOLOGIES; DATA SPARSITIES; DATA-DRIVEN; DATA-DRIVEN METHODS; INFLECTIVE LANGUAGE; LANGUAGE MODELING; LANGUAGE MODELS; LARGE VOCABULARY SPEECH RECOGNITION; MINIMUM ENTROPIES; N-GRAM MODELS; PRIOR KNOWLEDGE; PROBABILISTIC LANGUAGES; SLOVENIAN LANGUAGES; SPEECH DATABASE; STATISTICAL LANGUAGE MODELING; SUBWORD; SUBWORD UNITS; TEST SET PERPLEXITIES; TEST SETS; TEXT CORPORA; TRAINING CORPORA; WORD-BASED MODELS;

COMPUTATIONAL LINGUISTICS; EXPERIMENTS; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 65249183154     PISSN: 02180014     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218001409007119     Document Type: Article

References (32)

1. D. W. Aha, D, Kibler and M. Albert, Instance-based learning algorithms, Mach. Learn. 6 (1991) 37-66.
2. E. Arisoy, H. Dutagaci and L. M. Arslan, A unified language model for large vocabulary continuous speech recognition of Turkish, Sign. Process. 86(10) (2006) 2844-2862.
3. E. Brill, Transformation-based error-driven learning and natural language processing: a case study in part of speech tagging, Comput. Ling. 21(4) (1995).
4. W. Byrne, J. Hajič, P. Ircing, F. Jelinek, S. Khudanpur, P. Krbec and J. Psutka, On large vocabulary continuous speech recognition of highly inflectional language - Czech, Proc. Eurospeech (2001).
5. H. Cerf-Danon and M. El-Beze, Three different probabilistic language models: comparison and combination, Proc. ICASSP 1 (1991) 297-300.
6. G. Choueiter, D. Povey, S. F. Chen and G. Zweig, Morpheme-based language modeling for Arabic LVCSR, Proc. ICASSP 1 (2007) 1053-1056.
7. M. Creutz and K. Lagus, Inducing the morphological lexicon of a natural language from unannotated text, Proc. Int. Interdisciplinary Conf. Adaptive Knowledge Representation and Reasoning (AKRR'05), Espoo, Finland, 15-17 June, 2005, pp. 106-113.
8. N. Deshmukh, A. Ganapathiraju, J. Hamaker and J. Picone, Large Vocabulary Conversational Speech Recognition, http://www.isip.msstate.edu/projects/speech/ , Mississippi State University, Mississippi State, Mississippi, USA (1999).
9. J. Goldsmith, Unsupervised learning of the morphology of a natural language, Comput. Ling. 27 (2001) 153-198.
10. S. Goldwater, T. L. Griffiths and M. Johnson, Contextual dependencies in unsupervised word segmentation, Proc. Coling/ACL (2006).
11. J. Hajǐc and B. Hladka, Tagging inflective languages: prediction of morphological categories for a rich, structured tagset, Proc. ACL/Coling (1997) pp. 483-490.
12. T. Hirsimäki, M. Creutz, V. Siivola, M. Kurimo, S. Virpioja and J. Pylkkönen, Unlimited vocabulary speech recognition with morph language models applied to Finnish, Comput. Speech Lang. 20(4) (2006) 515-541.
13. M. Jardino and G. Adda, Automatic word classification using simulated annealing, Proc. ICASSP 2 (1993) 41-44.
14. F. Jelinek, Statistical Methods for Speech Recognition (MIT Press, Cambridge, MA, 1997).
15. Z. Kǎcǐc, B. Horvat and A. Zögling, Issues in design and collection of large telephone speech corpus for slovenian language, Proc. LREC (2000), pp. 943-946.
16. J. Kneissler and D. Klakow, Speech recognition for huge vocabularies by using optimized subword units, Proc. Eurospeech (2001), pp. 69-72.
17. L. Kontorovich, D. Ron and Y. Singer, A Markov model for the acquisition of morphological structure, Technical Report, CMU-CS-03-147, Carnegie Mellon University, Pittsburgh, PA (2003).
18. M. Kurimo, A. Puurula, E. Arisoy, V. Siivola, T. Hirsimaki, J. Pylkkonen, T. Alumae and M. Saraclar, Unlimited vocabulary speech recognition for agglutinative languages, Human Language Technology, Conf. North American Chapter of the Association for Computational Linguistics, HLT-NAACL, New York, USA (5-7 June, 2006).
19. M. Kurimo, M. Creutz and V. Turunen, Overview of morpho challenge in CLEF 2007, Unsupervised Morpheme Analysis - Morpho Challenge 2007, Working Notes for the CLEF 2007Workshop, Budapest, Hungary, URL: http://www.cis.hut.fi/ morphochallenge2007/.
20. O.-W. Kwon and J. Park, Korean large vocabulary continuous speech recognition with morpheme-based recognition units, Speech Commun. 39(3-4) (2003) 287-300.
21. M. Liwicki and H. Bunke, Handwriting recognition of whiteboard notes studying the influence of training set size and type, Int. J. Patt. Recogn. Artifi. Intell. 21(1) (2007) 83-98.
22. M. G. Malkovsky, Dialogue with an Artificial Intelligence System, Moscow State University, Moscow, Russia (1985) (in Russian).
23. G. Maltese and F. Mancini, A technique to automatically assign parts-of-speech to words taking into account word-ending information through a probabilistic model, Proc. Eurospeech (1991), pp. 753-756.
24. R. Rosenfeld, Two decades of statistical language modeling: where do we go from here? Proc. IEEE 88 (2000) 1270-1278.
25. T. Rotovnik, M. S. Maučec and Z. Kačič, Large vocabulary continuous speech recognition of an inflected language using stems and endings, Speech Commun. 49(6) (2007) 437-452.
26. M. S. Maučec, T. Rotovnik and M. Zemljak, Modeling highly inflected Slovenian language, Int. J. Speech Technol. 6 (2003) 245-257.
27. M. Snover and M. R. Brent, A probabilistic model for learning concatenative morphology, Proc. NIPS (2003), pp. 1513-1520.
28. A. Stolcke, SRILM an extensible language modeling toolkit, Proc. ICSLP (2002), 901-904.
29. B. K. Tsou, T. B. Y. Lai, K. K. Sin and L. Y. L. Cheung, Court stenography-to-text (STT) in Hong Kong: a jurilinguistic engineering effort, Int. J. Patt. Recogn. Artifi. Intell. 19(2/3) (2006) 99-107.
30. X. Wang, D. S. Yeung, J. N. K. Liu, R. Luk and X. Wang, Hybrid language model based on statistics and linguistic rules, Int. J. Patt. Recogn. Artifi. Intell. 19(1) (2005) 109-128.
31. E. W. D. Whittaker and P. C. Woodland, Particle-based language modeling, Proc. ICSLP, Beijing, China (2000).
32. P. Witschel, Constructing linguistic oriented language models for large vocabulary speech recognition, Proc. Eurospeech (1993), pp. 1199-1202.