A general artificial neural network extension for HTK

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

Volumn 2015-January, Issue , 2015, Pages 3581-3585

  Zhang, C ^a   Woodland, P C ^a  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE EXTRACTION; HIDDEN MARKOV MODELS; HYBRID SYSTEMS; MARKOV PROCESSES; NEURAL NETWORKS; PROGRAM PROCESSORS; SPEECH COMMUNICATION; SPEECH PROCESSING;

ACOUSTIC MODELLING; ACTIVATION FUNCTIONS; FEED-FORWARD ARCHITECTURES; HIDDEN MARKOV MODEL TOOLKITS; PROCESSING TECHNIQUE; SPEAKER ADAPTATION; STATE-OF-THE-ART PERFORMANCE; WALL STREET JOURNAL;

SPEECH RECOGNITION;

EID: 84959142742     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (40)

1. http: //htk. eng. cam. ac. uk
2. S. J. Young, G. Evermann, M. J. F. Gales, T. Hain., D. Kershaw, X.-Y. Liu, G. Moore, J. J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. C. Woodland, The HTK book (for HTK version3. 4). Cambridge University Engineering Department, 2006.
3. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-basedstate tying for high accuracy acoustic modelling, " Proc. HumanLanguage Technology Workshop, Plainsboro, NJ, USA: MorganKaufman Publishers Inc, 1994.
4. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linearregression for speaker adaptation of continuous density hiddenMarkov models, " Computer Speech & Language, Vol. 9, No. 2, pp. 171-185, 1995.
5. D. Povey and P. C. Woodland, "Minimum phone errorand I-smoothing for improved discriminative training, " Proc. ICASSP'02, Orland o, FL, USA, 2002.
6. H. Zen, T. Nose, J. Yamagishi, S. Sako, T. Masuko, A. W. Black, and K. Tokuda, "The HMM-based speech synthesis system (HTS)version 2. 0, " Proc. 6th ISCA Workshop on Speech Synthesis, Bonn, Germany, 2007.
7. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineeringin context-dependent deep neural networks for conversationalspeech transcription, " Proc. ASRU'11, Waikoloa, HI, USA, 2011.
8. G. E. Hinton, L. Deng, D. Yu et al., "Deep neural networks foracoustic modeling in speech recognition, " IEEE Signal ProcessingMagazine, pp. 2-17, Nov. 2012.
9. G. E. Hinton and R. Salakhutdinov, "Reducing the dimensionalityof data with neural networks, " Science, vol. 313, no. 5786, pp. 504-507, Jul 2006.
10. Y. Bengio, "Learning deep architectures for AI, " Foundations and trends® in Machine Learning, Vol. 2, No. 1, pp. 1-127, 2009.
11. B. Kingsbury, T. N. Sainath, and H. Soltau, "Scalable minimumBayes risk training of deep neural network acoustic models usingdistributed Hessian-free optimization, " Proc. Interspeech'12, Portland, OR, USA, 2012.
12. G. Saon, H. Soltau, A. Emami, and M. Picheny, "Unfoldedrecurrent neural networks for speech recognition, " Proc. Interspeech'14, Singapore, 2014.
13. Z.-J. Yan, Q. Huo, and J. Xu, "A scalable approach to usingDNN-derived features in GMM-HMM based acoustic modelingfor LVCSR, " Proc. Interspeech'13, Lyon, France, 2013.
14. T. Mikolov, "Statistical language models based on neural networks, "Ph. D. dissertation, Ph. D. Thesis, Brno University of Technology, 2012.
15. X. Chen, Y.-Q. Wang, X.-Y. Liu, M. J. F. Gales, and P. C. Woodland, "Efficient GPU-based training of recurrent neural networklanguage models using spliced sentence bunch, " Proc. Interspeech'14, Singapore, 2014.
16. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlcek, Y.-M. Qian, P. Schwarz, J. Silovský, G. Stemmer, and K. Veselý, "The Kaldi speech recognitiontoolkit, " Proc. ASRU'11, Waikoloa, HI, USA, 2011.
17. S. Wiesler, A. Richard, P. Golik, R. Schlüter, and H. Ney, "RASR/NN: The RWTH neural network toolkit for speech recognition, "Proc. ICASSP'14, Florence, Italy, 2014.
18. D. Johnson, "Quicknet, " http: //www1. icsi. berkeley. edu/speech/qn. html.
19. X.-Y. Liu, F. Flego, L.-L. Wang, C. Zhang, M. J. F. Gales, and P. C. Woodland, "The Cambridge University 2014 BOLT conversationaltelephone Mand arin Chinese LVCSR system for speechtranslation, " Proc. Interspeech'15, Dresden, Germany, 2015.
20. H.-P. Wang, A. Ragni, M. J. F. Gales, K. M. Knill, P. C. Woodland, and C. Zhang, "Joint decoding of tand em and hybrid systemsfor improved keyword spotting on low resource languages, " Proc. Interspeech'15, Dresden, Germany, 2015.
21. H. Su, G. Li, D. Yu, and F. Seide, "Error back propagation forsequence training of context-dependent deep networks for conversationalspeech transcription, " Proc. ICASSP'13, Vancouver, Canada, 2013.
22. K. Veselý, A. Ghoshal, L. Burget, and D. Povey, "Sequencediscriminativetraining of deep neural networks, " Proc. Interspeech'13, Lyon, France, 2013.
23. P. Swietojanski and S. Renals, "Learning hidden unit contributionsfor unsupervised speaker adaptation of neural networkacoustic models, " Proc. IWSLT'14, Lake Tahoe, USA, Dec. 2014.
24. D. Yu, K. Yao, H. Su, G. Li, and F. Seide, "KL-divergence regularizeddeep neural network adaptation for improved large vocabularyspeech recognition, " Proc. ICASSP'13, Vancouver, Canada, 2013.
25. C. Zhang and P. C. Woodland, "Parameterised sigmoid and ReLUhidden activation functions for DNN acoustic modelling, " Proc. Interspeech'15, Dresden, Germany, 2015.
26. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker adaptationof neural network acoustic models using i-vectors, " Proc. ASRU'13, Olomouc, Czech Republic, 2013.
27. C. M. Bishop, Pattern recognition and machine learning. Springer, 2006.
28. F. Bastien, P. Lamblin, R. Pascanu, J. Bergstra, I. J. Goodfellow, A. Bergeron, N. Bouchard, and Y. Bengio, "Theano: new featuresand speed improvements, " Proc. Deep Learning and UnsupervisedFeature Learning NIPS Workshop, Lake Tahoe, USA, 2012.
29. D. Yu, A. Eversole, M. Seltzer, K. Yao, Z. Huang, B. Guenter, O. Kuchaiev, Y. Zhang, F. Seide, H. Wang, J. Droppo, G. Zweig, C. Rossbach, J. Currey, J. Gao, A. May, B. Peng, A. Stolcke, and M. Slaney, "An introduction to computational networks and thecomputational network toolkit, " Microsoft, Tech. Rep. MSR-TR-2014-112, 2014.
30. M. D. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q. V. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean, and G. E. Hinton, "On rectified linear units for speech processing, " Proc. ICASSP'13, Vancouver, Canada, 2013.
31. A. Senior and X. Lei, "Fine context, low-rank, softplus deep neuralnetworks for mobile speech recognition, " Proc. ICASSP'14, Florence, Italy, 2014.
32. N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networksfrom overfitting, " The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
33. J. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methodsfor online learning and stochastic optimization, " The Journal ofMachine Learning Research, vol. 12, pp. 2121-2159, 2011.
34. E. McDermott, G. Heigold, P. J. Moreno, A. Senior, and M. Bacchiani, "Asynchronous stochastic optimization for sequence trainingof deep neural networks: Towards big data, " Proc. Interspeech'14, Singapore, 2014.
35. X.-Y. Liu, M. J. F. Gales, and P. C. Woodland, "Automatic complexitycontrol for HLDA systems, " Proc. ICASSP'03, HongKong, 2003.
36. M. J. F. Gales, "Semi-tied covariance matrices for hidden Markovmodels, " IEEE Transactions on Speech and Audio Processing, vol. 7, no. 3, pp. 272-281, 1999.
37. M. J. F. Gales, "Maximum likelihood linear transformations forHMM-based speech recognition, " Computer speech & language, vol. 12, no. 2, pp. 75-98, 1998.
38. L. Deng, D. Yu, and J. Platt, "Scalable stacking and learningfor building deep architectures, " Proc. ICASSP'12, Kyoto, Japan, 2012.
39. C. Zhang and P. C. Woodland, "Stand alone training ofcontext-dependent deep neural network acoustic models, " Proc. ICASSP'14, Florence, Italy, 2014.
40. P. Swietojanski, A. Ghoshal, and S. Renals, "Revisiting hybridand GMM-HMM system combination techniques, " Proc. ICASSP'13, Vancouver, Canada, 2013.