Continuous digit recognition in noise: Reservoirs can do an excellent job!

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 3, Issue , 2012, Pages 1802-1805

  Jalalvand, Azarakhsh ^a   Triefenbach, Fabian ^a   Martens, Jean Pierre ^a  

^a GHENT UNIVERSITY   (Belgium)

Author keywords

Acoustic modeling; Model adaptation; Noise robustness; Reservoir computing

Indexed keywords

ACOUSTIC MODELING; DIGIT RECOGNITION; HMM-BASED SYSTEMS; MODEL ADAPTATION; NOISE ROBUSTNESS; NOISY CONDITIONS; NON-PARAMETRIC; RESERVOIR COMPUTING;

COMPUTER SIMULATION;

COMPUTER APPLICATIONS;

EID: 84878591993     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. J. F. Gemmeke, "Noise robust asr: Missing data techniques and beyond," Ph.D. dissertation, Radboud Universiteit Nijmegen, The Netherlands, 2011.
2. C. Chia-Ping and J. A. Bilmes, "Mva processing of speech features," IEEE Transactions on Audio, Speech and Language processing, 2007.
3. R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. De Mori, "Linear hidden transformation for adaptation of hybrid ann/hmm models," Speech Communication, vol. 49, pp. 827-835, 2007.
4. H. Jaeger, "The "echo state" approach to analysing and training recurrent neural networks," 2001. [Online]. Available: http://www.faculty.jacobsuniversity.de/hjaeger/pubs/EchoStatesTechRep.pdf
5. A. Jalalvand, F. Triefenbach, D. Verstraeten, and J.-P. Martens, "Connected digit recognition by means of reservoir computing," in Proc. of INTERSPEECH, 2011, pp. 1725-1728.
6. F. Triefenbach, A. Jalalvand, B. Schrauwen, and J.-P. Martens, "Phoneme recognition with large hierarchical reservoirs," in Proc. Advances in Neural Information Processing Systems (NIPS), 2010, pp. 2307-2315.
7. D. Verstraeten, B. Schrauwen, M. D'Haene, and D. Stroobandt, "An experimental unification of reservoir computing methods," Neural Networks, vol. 20, pp. 391-403, 2007.
8. H. Hirsh and D. Pearce, "The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ASR, 2000.