Large vocabulary speech recognition on parallel architectures

IEEE Transactions on Audio, Speech and Language Processing

Volumn 21, Issue 11, 2013, Pages 2290-2300

  Cardinal, Patrick ^a   Dumouchel, Pierre ^b   Boulianne, Gilles ^a  

^a Cent de Recherche Informatique de Montreal   (Canada)

^b ÉCOLE DE TECHNOLOGIE SUPÉRIEURE   (Canada)

Author keywords

GPU; multicore; parallel; speech recognition

Indexed keywords

GPU; GRAPHICS PROCESSING UNIT; INTEGRATION CAPACITY; LARGE VOCABULARY SPEECH RECOGNITION; MULTI CORE; MULTI-CORE PROCESSOR ARCHITECTURES; PARALLEL; PARALLEL IMPLEMENTATIONS;

COMPUTER GRAPHICS; NETWORK ARCHITECTURE; PARALLEL ARCHITECTURES; PROGRAM PROCESSORS; SPEECH RECOGNITION;

COMPUTER GRAPHICS EQUIPMENT;

EID: 84886675337     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2013.2271591     Document Type: Article

References (37)

1. P. Cardinal, G. Boulianne, and P. Dumouchel, The A, speech recognition systems on parallel architectures, in Int. Conf. Inf. Sci., Signal Process., their Applicat. (ISSPA), Jul. 2-5, 2012, pp. 108-113.
2. P. Cardinal, P. Dumouchel, and G. Boulianne, Parallel architectures in speech recognition, in Proc. 10th Annu. Conf. Int.Commun. Assoc. (Interspeech), Sep. 6-10, 2009, pp. 3039-3042.
3. P. Cardinal, P. Dumouchel, and G. Boulianne, Using A, for the parallelization of speech recognition systems, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Mar. 25-30, 2012, pp. 4433-4436.
4. P. Cardinal, P. Dumouchel, G. Boulianne, and M. Comeau, GPU accelerated acoustics likelihood computations, in Proc. 9th Annu. Conf. Int. Commun. Assoc. (Interspeech), Sep. 22-26, 2008, pp. 964-967.
5. J. Chong, E. Gonina, Y. Yi, and K. Keutzer, A fully parallel WFSTbased large vocabulary continuous speech recognition on a graphics processing unit, in Proc. 10th Annu. Conf. Int. Commun. Assoc. (Interspeech), Sep. 6-10, 2009, pp. 1183-1186.
6. J. Chong, E. Gonina, K. You, and K. Keutzer, Exploring recognition network representations for efficient speech inference on highly parallel platforms, in Proc. 11th Annu. Conf. Int. Commun. Assoc. (Interspeech), Sep. 26-30, 2010, pp. 1489-1492.
7. T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein, Introduction to Algorithms, 2nd ed. Cambridge, MA, USA: MIT Press, 2001.
8. CUDA [Online]. Available: http://www.nvidia.com/object/cuda home. html
9. G. Dahl, D. Yu, L. Deng, and A. Acero, Context-dependent Pre-trained deep neural networks for large vocabulary speech recognition, IEEE Trans. Audio, Speech, Lang. Process., Special Issue Deep Learn. Speech Lang. Process., vol. 20, no. 1, pp. 30-42, Jan. 2012.
10. J. Dean, G. Corrado, R. Monga, K. Chen, M. Devin, Q. Le, M. Mao, M. Ranzato, A. Senior, P. Tucker, K. Yang, and A. Ng, Large scale distributed deep networks, in Proc. Neural Inf. Process. Syst. Conf. (NIPS), Dec. 3-8, 2012.
11. P. R. Dixon, D. A. Caseiron, T. Oonishi, and S. Furui, The Titech large vocabulary WFST speech recognition system, in Proc. IEEE Workshop Autom. Speech Recogn. Understand. (ASRU), Dec. 13-17, 2007, pp. 443-448.
12. P. R. Dixon, T. Oonishi, and S. Furui, Fast acoustic computations using graphics processors, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Apr. 19-24, 2009, pp. 4321-4324.
13. P. R. Dixon, T. Oonishi, and S. Furui, Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition, Comput. Speech Lang., vol. 23, no. 4, pp. 510-526, 2009.
14. K. Gupta and J. D. Owens, Three-layer optimizations for fast GMM computations on GPU-like parallel processors, in Proc. IEEE Workshop Autom. Speech Recogn. Understand. ASRU '09, Dec. 13-17, 2009, pp. 146-151.
15. K. Gupta and J. D. Owens, Compute & Memory optimizations for high-quality speech recognition on low-end GPU processors, Proc. 18th Int. Conf. High Perform. Comput. (HiPC), pp. 1-10, Dec. 18-21, 2011.
16. P. Harish and P. J. Narayanan, Accelerating large graph algorithms on the GPU using CUDA, in Proc. 14th Int. Conf. High Perform. Comput. (HiPC), Dec. 19-22, 2007, pp. 197-208, Springer-Verlag.
17. M. Harris, Mapping computational concepts to GPUs, in GPU Gems 2. New York, NY, USA: Addison Wesley, 2005.
18. S. Ishikawa, K. Yamabana, R. Isotani, and A. Okumura, Parallel LVCSR algorithm for cellphone-oriented multicore processors, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 2006, pp. 177-180.
19. J. Van?k, J. Trmal, J. V. Psutka, and J. Psutka, Full covariance Gaussian mixture models evaluation on GPU, in Proc. IEEE Int. Symp. Signal Process. Inf. Technol., Dec. 12-15, 2012, pp. 203-207.
20. P. Kenny, R. Hollan, G. Boulianne, H. Garudadri, M. Lennig, and D. O'Shaugnessy, An A, algorithmfor very large vocabulary continuous speech recognition, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1992, vol. 1.
21. J. Kim, J. Chong, and I. R. Lane, Efficient on-the-fly hypothesis rescoring in a hybrid GPU/CPU-based large vocabulary continuous speech recognition engine, in Proc. 13th Annu. Conf. Int. Commun. Assoc. (Interspeech), Sep. 9-13, 2012.
22. J. Kim and W. Sung, Multi-user Real-time speech recognition with a GPU, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Mar. 25-30, 2012, pp. 1617-1620.
23. J. Kim, K. You, and W. Sung, H- and C-level WFST-based large vocabulary continuous speech recognition on graphics processing units, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), May 22-27, 2011, pp. 1733-1736.
24. P. Kveton andM. Novak, Accelerating hierachical acoustic likelihood computation on graphics processors, in Proc. 11th Annu. Conf. Int. Commun. Assoc. (Interspeech), Sep. 26-30, 2010, pp. 350-353.
25. A. Lumsdaine, D. Gregor, B. Hendrickson, and J. W. Berry, Challenges in parallel graph processing, Parallel Process. Lett., pp. 5-20, 2007. (Pubitemid 46573923)
26. M. Mohri, Finite-state transducers in language and speech processing, Comput. Linguist., vol. 23, no. 2, pp. 269-311, Jun. 1997.
27. M. Mohri, F. C. N. Pereira, and M. Riley, Weighted automata in text and speech processing, in Proc. 12th Biennial Eur. Conf. Artif. Intell. (ECAI-96), Workshop Extended Finite State Models of Lang., 1996.
28. M. Mohri, F. C. N. Pereira, and M. Riley, Weighted finite-state transducers in speech recognition, in Proc. ISCA Tutorial and Research Workshop, Autom. Speech Recogn.: Challenges for the New Millenium (ASR '00), 2000.
29. M. Mohri, F. C. N. Pereira, and M. Riley, Weighted finite-state transducers in speech recognition, Comput. Speech Lang., 2002.
30. N. Morgan, Deep and Wide: Multiple Layers in Automatic Speech Recognition, IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 1, pp. 7-13, Jan. 2012.
31. NVidia CUDA Compute Unified Device Architecture: Programming Guide, NVidia, 2007.
32. N. Parihar, R. Schluter,D. Rybach, and E.A. Hansen, Parallel Lexicaltree based LVCSR on Multi-core processors, in Proc. Interspeech, Sep. 26-30, 2010, pp. 1485-1488.
33. D. B. Paul, Algorithms for an optimal A, search and linearizing the search in the stack decoder, in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., 1991, vol. 1.
34. S. Phillips and A. Roggers, Parallel speech recognition, Int. J. Parallel Program., vol. 27, no. 4, pp. 257-288, Aug. 1999.
35. S. Russel and P. Norvig, Artificial Intelligence: A Modern App.roach. Englewood Cliffs, NJ, USA: Prentice-Hall, 1994.
36. J. Vanek, J. Trmal, J. V. Psutka, and J. Psutka, Optimized acoustic likelihoods computation for NVIDIA and ATI/AMD graphics processors, IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 6, pp. 1818-1828, Aug. 2012.
37. K. You, J. Chong, Y. Yi, E. Gonina, C. J. Hughes, Y. K. Chen, W. Sung, and K. Keutzer, Parallel scalability in speech recognition, IEEE Signal Process. Mag., vol. 26, no. 6, pp. 124-135, Nov. 2009.