Purely sequence-trained neural networks for ASR based on lattice-free MMI

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

Volumn 08-12-September-2016, Issue , 2016, Pages 2751-2755

  Povey, Daniel ^a,b   Peddinti, Vijayaditya ^a   Galvez, Daniel ^c   Ghahremani, Pegah ^a   Manohar, Vimal ^a   Na, Xingyu ^d   Wang, Yiming ^a   Khudanpur, Sanjeev ^a,b  

^a Johns Hopkins University   (United States)

^b JOHNS HOPKINS UNIVERSITY   (United States)

^c Department of Obstetrics Gynecology   (United States)

^d Lele Innovation and Intelligence Technology (Beijing) Co   (China)

Author keywords

Neural networks; Sequence discriminative training

Indexed keywords

COMPUTATIONAL LINGUISTICS; ENTROPY; IMAGE CODING; NEURAL NETWORKS; PROGRAM PROCESSORS; SPEECH COMMUNICATION; SPEECH PROCESSING; SPEECH RECOGNITION; STEREOPHONIC BROADCASTING;

DISCRIMINATIVE TRAINING; FORWARD / BACKWARD ALGORITHMS; MAXIMUM MUTUAL INFORMATION; N-GRAM LANGUAGE MODELS; OBJECTIVE FUNCTIONS; SPACE AND TIME COMPLEXITY; TRAINED NEURAL NETWORKS; WORD ERROR RATE REDUCTIONS;

COMPLEX NETWORKS;

EID: 84994310412     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: 10.21437/Interspeech.2016-595     Document Type: Conference Paper

References (23)

1. B. Kingsbury, "Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling," in Proceedings of ICASSP. IEEE, apr 2009, pp. 3761-3764.
2. K. Veselý, A. Ghoshal, L. Burget, and D. Povey, "Sequencediscriminative training of deep neural networks." in Proceedings of INTERSPEECH, 2013, pp. 2345-2349.
3. H. Su, G. Li, D. Yu, and F. Seide, "Error back propagation for sequence training of Context-Dependent Deep Networks for conversational speech transcription," in Proceedings of ICASSP. IEEE, may 2013, pp. 6664-6668.
4. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge University, 2005.
5. A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, "Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks," in Proceedings of the 23rd international conference on Machine learning. ACM, 2006, pp. 369-376.
6. H. Sak, A. Senior, K. Rao, O. Irsoy, A. Graves, F. Beaufays, and J. Schalkwyk, "Learning acoustic frame labeling for speech recognition with recurrent neural networks," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on. IEEE, 2015, pp. 4280-4284.
7. A. Hannun, C. Case, J. Casper, B. Catanzaro, G. Diamos, E. Elsen, R. Prenger, S. Satheesh, S. Sengupta, A. Coates et al., "Deep speech: Scaling up end-to-end speech recognition," arXiv preprint arXiv:1412.5567, 2014.
8. H. Sak, A. Senior, K. Rao, and F. Beaufays, "Fast and accurate recurrent neural network acoustic models for speech recognition," in Sixteenth Annual Conference of the International Speech Communication Association, 2015.
9. A. Senior, H. Sak, F. de Chaumont Quitry, T. N. Sainath, and K. Rao, "Acoustic Modelling with CD-CTC-SMBR LSTM RNNS," in ASRU, 2015.
10. S. Chen, B. Kingsbury, Lidia Mangu, D. Povey, G. Saon, H. Soltau, and G. Zweig, "Advances in speech transcription at IBM under the DARPA EARS program," IEEE Transactions on Audio, Speech and Language Processing, vol. 14, no. 5, pp. 1596-1608, sep 2006.
11. M. Mohri, F. Pereira, and M. Riley, "Speech recognition with weighted finite-state transducers," in Springer Handbook of Speech Processing. Springer, 2008, pp. 559-584.
12. J. Hopcroft, "An n log n algorithm for minimizing states in a finite automaton," Theory of Machines and Computations, pp. 189-196, 1971.
13. D. Povey, M. Hannemann, G. Boulianne, L. Burget, A. Ghoshal, M. Janda, M. Karafiát, S. Kombrink, P. Motlicek, Y. Qian et al., "Generating exact lattices in the wfst framework," in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on. IEEE, 2012, pp. 4213-4216.
14. V. Peddinti, D. Povey, and S. Khudanpur, "A time delay neural network architecture for efficient modeling of long temporal contexts," in Proceedings of INTERSPEECH, 2015.
15. (2016) Readme file in code repository to replicate the experiments in this paper. [Online]. Available: https://github.com/vijayaditya/kaldi/blob/chain paper results/egs/README paper results
16. T. Ko, V. Peddinti, D. Povey, and S. Khudanpur, "Audio augmentation for speech recognition," in Proceedings of INTERSPEECH, 2015.
17. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker adaptation of neural network acoustic models using i-vectors," in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on, Dec 2013, pp. 55-59.
18. G. Chen, H. Xu, M. Wu, D. Povey, and S. Khudanpur, "Pronunciation and silence probability modeling for ASR," in Proceedings of INTERSPEECH, 2015.
19. H. Sak, A. Senior, and F. Beaufays, "Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition," Feb. 2014. [Online]. Available: http://arxiv.org/abs/1402.1128
20. A. Rousseau, P. Deléglise, and Y. Esteve, "Ted-lium: an automatic speech recognition dedicated corpus." in LREC, 2012, pp. 125-129.
21. V. Peddinti, V. Manohar, Y. Wang, D. Povey, and S. Khudanpur, "Far-field ASR without parallel data," in Proceedings of Interspeech, 2016. [Online]. Available: http://www.danielpovey.com/files/2016 interspeech ami.pdf
22. A.-r. Mohamed, F. Seide, D. Yu, J. Droppo, A. Stolcke, G. Zweig, and G. Penn, "Deep bi-directional recurrent networks over spectral windows," in Proceedings of ASRU. ASRU, 2015.
23. G. Saon, H.-K. J. Kuo, S. Rennie, and M. Picheny, "The IBM 2015 English Conversational Telephone Speech Recognition System," may 2015. [Online]. Available: http://arxiv.org/abs/1505.05899