Robust ASR using Support Vector Machines

Speech Communication

Volumn 49, Issue 4, 2007, Pages 253-267

  Solera Urena R ^a   Martin Iglesias D ^a   Gallardo Antolin A ^a   Pelaez Moreno C ^a   Diaz de Maria F ^a  

^a UNIVERSIDAD CARLOS III DE MADRID   (Spain)

Author keywords

Additive noise; ANN; Dynamic Time Alignment; HMM; Hybrid ASR; Kernel methods; Machine learning; Robust ASR; Support Vector Machines

Indexed keywords

ADDITIVE NOISE; HIDDEN MARKOV MODELS; NEURAL NETWORKS; PARAMETERIZATION; SUPPORT VECTOR MACHINES;

DYNAMIC TIME ALIGNMENT; HYBRID ASR; KERNEL METHODS; ROBUST ASR;

SPEECH RECOGNITION;

EID: 34047146422     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2007.01.013     Document Type: Article

References (56)

1. Allwein E., Schapire R., and Singer Y. Reducing multiclass to binary: a unifying approach for margin classifiers. J. Mach. Learn. Res. 1 (2000) 113-141
2. Bengio Y. Neural Networks for Speech and Sequence Recognition (1995), London International Thomson Computer Press, London, UK
3. Bourlard H., and Morgan N. Connectionist Speech Recognition: A Hybrid Approach (1994), Kluwer Academic, Boston, Norwell, MA
4. Burges C. Simplified support vector decision rules. Proc. 13th Internat. Conf. on Machine Learning (1996), Bari, Italy 71-77
5. Chih-Chung, C., Chih-Jen, L., 2004. LibSVM: a library for Support Vector Machines. Available from: .
6. Clarkson P., and Moreno P. On the use of Support Vector Machines for phonetic classification. IEEE Internat Conf. Acoust. Speech Signal Process. 2 (1999) 585-588
7. Collobert, R., SVMTorch: a Support Vector Machine for large-scale regression and classification problems, IDIAP. Available from: .
8. Crammer K., and Singer Y. On the algorithmic implementation of multiclass kernel-based vector machines. J. Mach. Learn. Res. 2 (2001) 265-292
9. Ech-Cherif, A., Kohili, M., Benyettou, A., Benyettou, M., 2002. Lagrangian Support Vector Machines for phoneme classification. In: Proc. 9th Internat. Conf. on Neural Information Processing (ICONIP'02), Vol. 5, Singapore, pp. 2507-2511.
10. Fine, S., Navratil, J., Gopinath, R., 2001. A hybrid GMM/SVM approach to speaker identification. In: Proc. Internat. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Salt Lake City, UT, USA, Vol. 1, pp. 417-420.
11. Fürnkranz J. Round robin classification. J. Mach. Learn. Res. 2 (2002) 721-747
12. Ganapathiraju, A., 2002. Support vector machines for speech recognition. PhD Thesis, Mississipi State University.
13. Ganapathiraju, A., Hamaker, J., Picone, J., 2000. Hybrid SVM/HMM architectures for speech recognition. In: Proc. 2000 Speech Transcription Workshop, Maryland, USA, Vol. 4, pp. 504-507.
14. Ganapathiraju A., Hamaker J., and Picone J. Applications of support vector machines to speech recognition. IEEE Trans. Signal Process. 52 (2004) 2348-2355
15. Gangashetty, S., Sekhar, C., Yegnanarayana, B., 2005. Combining evidence from multiple classifiers for recognition of consonant-vowel units of speech in multiple languages. In: Proc. Internat. Conf. on Intelligent Sensing and Information Processing, Chennai, India, pp. 387-391.
16. García-Cabellos, J., Peláez-Moreno, C., Gallardo-Antolín, A., Pérez-Cruz, F., Díaz-de-María, F., 2004. SVM classifiers for ASR: a discussion about parameterization. In: Proc. EUSIPCO 2004, Wien, Austria, pp. 2067-2070.
17. Glass J.R. A probabilistic framework for segment-based speech recognition. Comput. Speech Language 17 (2003) 137-152
18. Hamaker, J., Picone, J., 2003. Advances in speech recognition using sparse Bayesian methods, unpublished (January 2003).
19. Hamaker, J., Picone, J., Ganapathiraju, A. 2002. A sparse modeling approach to speech recognition based on relevance vector machines. In: Proc. Internat. Conf. on Spoken Language Processing, Denver, CO, USA, Vol. 2, pp. 1001-1004.
20. Hsu C., and Lin C. A comparison of methods for multi-class support vector machines. IEEE Trans. Neural Networks 13 2 (2002) 415-425
21. Iso, K., Watanabe, T., 1990. Speaker-independent word recognition using a neural prediction model. In: Proc. Internat. Conf.e on Acoustics, Speech and Signal Processing (ICASSP), Alburquerque, NM, USA, pp. 441-444.
22. Jaakkola, T., Haussler, D., 1998. Exploiting generative models in discriminative classifiers. Technical Report, Department of Computer Science, University of California. Available from: .
23. Jiang H., Li X., and Liu C. Large margin hidden Markov models for speech recognition. IEEE Trans. Audio Speech Language Process. 14 (2006) 1584-1595
24. Joachims T. Advances in kernel methods-support vector learning. In: Schölkopf B., Burges C.J.C., and Smola A.J. (Eds). Making Large Scale SVM Learning Practical (1999), MIT Press, Cambridge, MA 169-184
25. Le, Q., Bengio, S., 2003. Client dependent GMM-SVM models for speaker verification. In: Internat. Conf. on Artificial Neural Networks, ICANN/ICONIP. Springer-Verlag, Berlin, pp. 443-451.
26. Lin, H.T., Lin, C.J., Weng, R.C., 2003. A note on Platt's probabilistic outputs for Support Vector Machines. Technical Report, Department of computer science and information engineering, National Taiwan University.
27. Ma, C., Randolph, M., Drish, J., 2001. A Support Vector Machines-based rejection technique for speech recognition. In: Proc. Internat. Conf. Acoustics, Speech and Signal Processing (ICASSP), Salt Lake City, UT, USA, Vol. 1, pp. 381-384.
28. Martín-Iglesias, D., Bernal-Chaves, J., Peláez-Moreno, C., Gallardo-Antolín, A., Díaz-de-María, F., 2005. A speech recognizer based on multiclass SVMs with HMM-guided segmentation. In: Nonlinear Analyses and Algorithms for Speech Processing. Lecture Notes in Computer Science, Vol. LNAI 3817, Springer, pp. 256-266.
29. Moreno, A., 1998. SpeechDat documentation [cd-rom], ver 1.
30. Navia-Vázquez A., Pérez-Cruz F., Artés-Rodríguez A., and Figueiras-Vidal A. Weighted least squares training of support vector classifiers leading to compact and adaptive schemes. IEEE Trans. Neural Networks 12 5 (2001) 1047-1059
31. Osuna, E., Freund, R., Girosi, F., 1997. An improved training algorithm for Support Vector Machines. In: IEEE Workshop on Neural Networks for Signal Processing, Amelia Island, FL, USA, pp. 276-285.
32. Platt, J.C., 1999. Probabilities for SV machines. In: Advances in Large Margin Classifiers. MIT Press, pp. 61-74.
33. Rabiner L.R., Rosenberg A., and Levinson S. Considerations in dynamic time warping algorithms for discrete word recognition. IEEE Trans. Acoustics Speech Signal Process. 26 6 (1978) 575-582
34. Reichl, W., Ruske, G., 1995. A hybrid RBF-HMM system for continuous speech recognition. In: Proc. Internat. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Detroit, MI, USA, pp. 3335-3338.
35. Robinson, T., Hochberg, M., Renals, S., 1995. The Use of Recurrent Neural Networks in Continuous Speech Recognition. In: Automatic Speech and Speaker Recognition-Advanced Topics, Kluwer Academic Publishers, pp. 159-184 (Chap. 19).
36. Sakoe, H., Isotani, R., Yoshida, K., Iso, K., Watanabe, T., 1989. Speaker-independent word recognition using dynamic programming neural networks. In: Proc. Internat. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Glasgow, Scotland, pp. 439-442.
37. Schölkopf B., and Smola A. Learning with Kernels (2002), MIT Press, Cambridge, MA
38. Sekhar, C., Lee, W., Takeda, K., Itakura, F., 2003. Acoustic modelling of subword units using Support Vector Machines. In: Workshop on spoken language processing, Mumbai, India.
39. Shimodaira H., Noma K., Nakai M., and Sagayama S. Support vector machine with Dynamic Time-Alignment Kernel for speech recognition. Proc. Eurospeech (2001), Aalborg, Denmark 1841-1844
40. Shimodaira, H., Noma, K., Nakai, M., 2002. Dynamic time-alignment kernel in Support Vector Machine. In: Advances in Neural Information Processing Systems 14, Vol. 2. MIT Press, Cambridge, MA, pp. 921-928.
41. Smith, N., Gales, M., 2002. Using SVMs and discriminative models for speech recognition. In: IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, Vol. 1, Orlando, FL, USA, pp. 77-80.
42. Smith, N., Gales, M., 2002. Speech recognition using SVMs. In: Advances in Neural Information Processing Systems 14, Vol. 14. MIT Press, Cambridge, MA, pp. 1197-1204.
43. Smith, N., Niranjan, M., 2000. Data-dependent kernels in SVM classification of speech patterns. In: Proc. Internat. Conf. on Spoken Language Processing (ICSLP), Beijing, China, Vol. 1, pp. 297-300.
44. Stadermann, J., Rigoll, G., 2004. A hybrid SVM/HMM acoustic modeling approach to automatic speech recognition. In: Proc. Internat. Conf. on Spoken Language Processing (ICSLP), Jeju Island, Korea, pp. 661-664.
45. Tebelskis, J., Waibel, A., Petek, B., Schmidbauer, O., 1991. Continuous speech recognition using predictive neural networks. In: Proc. Internat. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, pp. 61-64.
46. Thubthong N., and Kijsirikul B. Support vector machines for Thai phoneme recognition. Internat. J. Uncertainty Fuzziness Knowledge-Based Syst. 9 (2001) 803-813
47. Trentin E., and Gori M. A survey of hybrid ANN/HMM models for automatic speech recognition. Neurocomputing 37 (2001) 91-126
48. Vapnik V. The Nature of Statistical Learning Theory (1995), Springer-Verlag, New York
49. Vapnik V. Statistical Learning Theory (1998), Wiley, Chichester, GB
50. Varga, A., Steenneken, J., Tolimson, M., Jones, D., 1992. The NOISEX-92 study on the effect of additive noise on automatic speech recognition. Technical Report, DRA Speech Research Unit.
51. Vicente-Peña J., Gallardo-Antolín A., Peláez-Moreno C., and Díaz-de-María F. Band-pass filtering of the time sequences of spectral parameters for robust wireless speech recognition. Speech Commun. 48 10 (2006) 1379-1398
52. Wan, V., Renals, S., 2003. Support vector machine speaker verification methodology. In: Internat. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Hong Kong, Vol. 2, pp. 221-224.
53. Weiss N.A., and Hasset M.J. Introductory Statistics. third ed. (1993), Addison-Wesley, Reading, MA
54. Weston, J., Watkins, C., 1999. Multi-class Support Vector Machines. In: M. Verleysen (Ed.), Proc. European Symposium on Artificial Neural Networks.
55. Wu T.F., Lin C.J., and Weng R.C. Probability estimates for multi-class classification by pairwise coupling. J. Mach. Learn. Res. 5 (2004) 975-1005
56. Young, S., 1995. HTK-Hidden Markov Model toolkit (ver 2.1), Cambridge University.