Feature-rich sub-lexical language models using a maximum entropy approach for German LVCSR

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2013, Pages 3404-3408

  Shaik, M Ali Basha ^a   El Desoky Mousa, Amr ^a   Schlüter, Ralf ^a   Ney, Hermann ^a,b  

^a RWTH AACHEN UNIVERSITY   (Germany)

^b UFR 919 Laboratoire d'Informatique Pour la Mécanique et les Sciences de l'Ingénieur   (France)

Author keywords

Class based; Features; German LVCSR; Maximum entropy; Open vocabulary

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; MAXIMUM ENTROPY METHODS; SPEECH PROCESSING;

CLASS-BASED; FEATURES; GERMAN LVCSR; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; MAXIMUM A POSTERIORI; MAXIMUM-ENTROPY APPROACHES; OPEN-VOCABULARY; PROBABILITY ESTIMATE;

COMPUTATIONAL LINGUISTICS;

EID: 84906223934     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. M. Bisani and H. Ney, "Open Vocabulary Speech Recognition with Flat Hybrid Models, " in Interspeech, Lisbon, Portugal, Sep. 2005, pp. 725 - 728.
2. M. Shaik, A. El-Desoky, R. Schlüter, and H. Ney, "Hybrid Language Models Using Mixed Types of Sub-lexical Units for Open Vocabulary German LVCSR, " in Interspeech, Florence, Italy, Aug. 2011, pp. 1441 - 1444.
3. M. Shaik, A. El-Desoky, R. Schlüter, and H. Ney, "Using Morpheme and Syllable Based Sub-words for Polish LVCSR, " in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Prague, Czech Republic, May 2011, pp. 4680 - 4683.
4. A. El-Desoky, M. Shaik, R. Schlüter, and H. Ney, "Sub-lexical language models for German LVCSR, " in IEEEWorkshop on Spoken Language Technology, Berkeley, CA, USA, Dec. 2010, pp. 159 - 164.
5. P. Brown, P. deSouza, R. Mercer, V. D. Pietra, and J. Lai, "Classbased N-gram models of natural language, " Computational linguistics, vol. 18, pp. 467 - 479, 1992.
6. E. Jaynes. (1957) Information theory and statistical mechanics. Physical Review 106. [Online]. Available: http://bayes.wustl.edu/etj/articles/theory.1. pdf.
7. R. Rosenfeld, "Adaptive statistical language modeling: A Maximum Entropy approach, " Ph.D. dissertation, Carnegie Mellon University, 1994.
8. R. Sarikaya, M. Afify, Y. Deng, H. Erdogan, and Y. Gao, "Joint morphological-lexical language modeling for processing morphologically rich languages with application to dialectal Arabic, " vol. 16, no. 7, pp. 1330-1339, 2008.
9. S. F. Chen, "Performance prediction for exponential language models, " in Proc. Human Language Tech. Conf. of the North American Chapter of the ACL, Boulder, Colorado, USA, May 2009, pp. 450 - 458.
10. J. Cui, Y. Su, K. Hall, and F. Jelinek, "Investigating linguistic knowledge in a maximum entropy token-based language model, " in Proc. IEEE Automatic Speech Recognition and Understanding Workshop, Kyoto, Japan, Dec. 2007, pp. 171 - 176.
11. X. Zhu, S. F. Chen, and R. Rosenfeld, "Linguistic features for whole sentence maximum entropy language models, " in Proc. European Conf. on Speech Communication and Technology, Budapest, Hungary, Sep. 1999.
12. S. F. Chen, L. Mangu, B. Ramabhadran, R. Sarikaya, and A. Sethy, "Scaling shrinkage-based language models, " in Proc. IEEE Automatic Speech Recognition and Understanding Workshop, Merano, Italy, Dec. 2009, pp. 299-304.
13. G. Maltese, P. Bravetti, H. Crépy, B. J. Grainger, M. Herzog, and F. Palou, "Combining word- And class-based language models: A comparative study in several languages using automatic and manual word-clustering techniques, " in Interspeech, Aalborg, Denmark, Sep. 2001, pp. 21 - 24.
14. D. Oikonomidis and V. Digalakis, "Stem-based Maximum Entropy language models for inflectional languages, " in Proc. European Conf. on Speech Communication and Technology, Geneva, Switzerland, Sep. 2003, pp. 2285 - 2288.
15. A. El-Desoky, M. Shaik, R. Schl̈uter, and H. Ney, "Morpheme Level Feature-based Language Models for German LVCSR, " in Interspeech, Portland, OR, USA, Sep. 2012.
16. M. Creutz and K. Lagus, "Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0, " Computer and Information Science Helsinki University of Technology, Finland, Tech. Rep., Mar. 2005.
17. H. Schmid, "Improvements in Part-of-Speech Tagging with an application to German, " in ACL-SIGDAT-Workshop, Dublin, Ireland, Mar. 1995, pp. 47 - 50.
18. A. El-Desoky, M. Shaik, R. Schlüter, and H. Ney, "Morpheme Based Factored Language Models for German LVCSR, " in Interspeech, Florence, Italy, Aug. 2011, pp. 1445 - 1448.
19. A. Stolcke, "SRILM - An extensible language modeling toolkit, " in Proc. Int. Conf. on Spoken Language Processing, vol. 2, Denver, Colorado, USA, Sep. 2002, pp. 901 - 904.
20. C. Chelba and A. Acero, "Adaptation of Maximum Entropy Capitalizer: Little data can help a lot, " Computer Speech and Language, vol. 20, no. 4, pp. 382 - 399, 2006.
21. M. Shaik, A. El-Desoky, R. Schl̈uter, and H. Ney, "Investigation of Maximum Entropy Hybrid Language Models for Open Vocabulary German and Polish LVCSR, " in Interspeech, Portland, OR, USA, Sep. 2012.
22. T. Alumäe and M. Kurimo, "Efficient Estimation of Maximum Entropy Language Models with N-gram features: An SRILM extension, " in Interspeech, Chiba, Japan, September 2010.
23. C. Samuelsson and W. Reichl, "A class-based language model for large-vocabulary speech recognition extracted from part-ofspeech statistics, " in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 1, Phoenix, AZ, USA, Mar. 1999, pp. 537 - 540.
24. N. Parihar and J. Picone, "DSR Front End LVCSR Evaluation - AU/384/02, " Aurora Working Group, European Telecommunications Standards Institute, France, Tech. Rep., Dec. 2002.