Speeding-up Neural Network training using sentence and frame selection

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

Volumn 1, Issue , 2007, Pages 377-380

  Scanzio, Stefano ^a   Laface, Pietro ^a   Gemello, Roberto ^b   Mana, Franco ^b  

^a POLITECNICO DI TORINO   (Italy)

^b Loquendo SpA   (Italy)

Author keywords

Frame selection; Neural networks training; Sentence selection; Speech recognition

Indexed keywords

LINGUISTICS; NEURAL NETWORKS;

BACK-PROPAGATION ALGORITHM; FRAME SELECTION; LARGE AMOUNTS; NEURAL NETWORKS TRAININGS; PRIOR PROBABILITY; SENTENCE SELECTION; SOFTWARE OPTIMIZATION; SPEECH DATA; SPEED UP; TRAINING PROCESS;

SPEECH RECOGNITION;

EID: 56149088885     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. D. R. Wilson, and T. R. Martinez, "The General Inefficiency of Batch Training for Gradient Descent Learning," Neural Networks, Vol. 16, No. 10, pp. 1429-1451, 2003.
2. H. Bourlard, and N. Morgan, "Continuous Speech Recognition by Connectionist Statistical Methods," IEEE Trans. On Neural Networks, Vol. 4, No. 6, Nov. 1993, pp. 893-909, 1993.
3. C. Pelaez-Moreno, Q. Zhu, B. Chen, and N. Morgan, "Automatic data selection for MLP-based feature extraction for ASR," Proc. Interspeech 2005, pp. 229-232, 2005.
4. Q. Zhu, A. Stolcke, B. Y. Chen, and N. Morgan, "Using MLP Features in SRI.s Conversational Speech Recognition System," in Proc. Interspeech 2005, pp. 2141-2144, 2005.
5. D. Albesano, R. Gemello, and F. Mana, "Hybrid HMM-NN Modelling of Stationary-Transitional Units for Continuous Speech Recognition," Int. Conf. on Neural Information Processing 1997, pp. 1112-1115, 1997.
6. T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein, "Introduction to Algorithms," MIT Press and McGraw-Hill, 2001.
7. D. Albesano, R. Gemello, and F. Mana, "Hybrid HMM-NN for Speech recognition and Prior Class Probabilities," in Proceedings of the 9th International Conference on Neural Information Processing, vol. 5, pp. 2391-2394, 2002.
8. L. Yaeger, R. Lyon, and B. Webb, "Effective Training of Neural Network Character Classifier for Word Recognition," In Advances in Neural Information Processing Systems 9, MIT press, 1997.
9. D. Anguita, G. Parodi, and R. Zunino, "An Efficient Implementation of BP on RISC-based Workstations," Neurocomputing, no. 6, pp. 57-65, 1994.
10. J. Bilmes, K. Asanovic, C. Chin and J, Demmel, "Using Phipac to Speed Error Back-Propagation Learning," ICASSP 1997, vol. 5, pp. 4153-4157, 1997.
11. H. Schwenk, "Efficient Training of Large Neural Networks for Language Modeling," IJCNN 2004, pp. 3059-3062, 2004.
12. Intel's MKL Math Kernel Library" http://www.intel.com/cd/software/ products/asmona/eng/perflib/mkl
13. Intel's IPP Integrated Performance Primitives, http://www.intel.com/cd/ software/products/asmona/eng/perflib/ipp