Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition

2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings

Volumn , Issue , 2014, Pages 135-140

  Serizel, Romain ^a   Giuliani, Diego ^a  

^a FONDAZIONE BRUNO KESSLER   (Italy)

Author keywords

Automatic speech recognition; Children's speech recognition; Deep neural networks; Vocal tract length normalisation

Indexed keywords

DECODING; HIDDEN MARKOV MODELS; MARKOV PROCESSES; SPEECH;

ACOUSTIC FEATURES; AUTOMATIC SPEECH RECOGNITION; CHILDREN'S SPEECH RECOGNITION; DEEP NEURAL NETWORKS; MEL-FREQUENCY CEPSTRAL COEFFICIENTS; NORMALISATION; PHONE ERROR RATE; VOCAL TRACT LENGTHS;

SPEECH RECOGNITION;

EID: 84946692024     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SLT.2014.7078563     Document Type: Conference Paper

References (30)

1. W. T. Fitch and J. Giedd, "Morphology and development of the human vocal tract: A study using magnetic resonance imaging, " Journal of Acoust. Soc. Arner, vol. 1 06, no. 3, pp. 1 5 1 1-1 522, Sept. 1 999.
2. J. E. Huber, E. T. Stathopoulos, G. M. Curione, T. A. Ash, and K. Johnson, "Formants of children women and men: The effect of vocal intensity variation, " Journal of Acoust. Soc. Arner, vol. 1 06, no. 3, pp. 1 5 3 2-1 542, Sept. 1 999.
3. S. Lee, A. Potamianos, and S. Narayanan, "Acoustic of children 's speech : Developmental changes of temporal and spectral parameters, " Journal of Acoust. Soc. Arner, vol. 1 05, no. 3, pp. 1 4 5 5-1 468, March 1 999.
4. L. Lee and R. C. Rose, " Speaker Normalization Using Efficient Frequency Warping Procedure, " in Proc. ofIEEE ICASSP, Atlanta, GA, May 1 996, pp. 3 5 3-3 5 6.
5. S. Wegmann, D. McAI Ia ster, J. Orloff, and B. Peskin, "Speaker Normalisation on Conversational Telephone Speech, " in Proc. of iEEE ICASSP, Atlanta, GA, May 1 996, pp. 1-3 3 9-3 4 1.
6. E. Eide and H. Gish, "A Parametric Approach to Vocal Tract Lenght Normalization, " in Proc. of IEEE iCASSP, Atlanta, GA, May 1 996, pp. 3 46-3 49.
7. A. Hagen, B. Pellom, and R. Cole, "Children 's Speech Recognition with Application to Interactive Books and Tutors, " in Proc. of IEEE ASRU Workshop, St. Thomas Irsee, US Virgin Islands, Dec. 2003.
8. D. Giuliani and M. Gerosa, "Investigating Recognition of Children Speech, " in Proc. of IEEE ICASSP, vol. 2, Hong Kong, Apr. 2003, pp. 1 3 7-1 40.
9. H. A. Bourlard and N. Morgan, Connectionist speech recognition: A hybrid approach. Springer, 1 994, vol. 247.
10. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition, " IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 82-97, Nov 20 1 2.
11. A. Mohamed, G. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 1 4-22, Jan 20 1 2.
12. G. Dahl, D. Yu, L. Deng, and A. Acero, "Contextdependent pre-trained deep neural networks for largevocabulary speech recognition, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 3 0-42, Jan 20 1 2.
13. A. Metallinou and 1. Cheng, "Using Deep Neural Networks to Improve Proficiency Assessment for Children English Language Learners, " in Proc. of INTERSPEECH, 20 1 4, pp. 1 468-1 472.
14. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription, " in Proc. of IEEE ASRU Workshop, December 20 1 1.
15. R. Serizel and D. Giuliani, "Deep neural network adaptation for children's and adults' speech recognition, " in Proc. of the First Italian Computational Linguistics Conference, Pisa, IT, 20 1 4.
16. P. Swietojanski, A. Ghoshal, and S. Renals, "Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR, " in Proc. of IEEE SLT Workshop, Dec 20 1 2, pp. 246-25 1.
17. V.-B. Le, L. Lamel, and 1. Gauvain, "Multi-style ML features for BN transcription, " in Proc. of IEEE ICASSP, March 20 1 0, pp. 4866-4869.
18. S. Thomas, M. Seltzer, K. Church, and H. Hermansky, "Deep neural network features and semi-supervised training for low resource speech recognition, " in Proc. of IEEE ICASSP, May 20 1 3, pp. 6704-6708.
19. H. Liao, "Speaker adaptation of context dependent deep neural networks, " in Proc. of IEEE ICASSP, 20 1 3, pp. 7947-795 1.
20. O. Abdel-Hamid and H. Jiang, "Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition. " in Proc. of INTERSPEECH, 20 1 3, pp. 1 248-1 252.
21. M. Seltzer, D. Yu, and Y. Wang, "An investigation of deep neural networks for noise robust speech recognition, " in Proc. of IEEE ICASSP, 20 1 3.
22. A. Senior and I. Lopez-Moreno, "Improving DNN speaker independence with I-vector inputs, " in Proc. of IEEE ICASSP, 20 1 4.
23. L. Welling, S. Kanthak, and H. Ney, "Improved Methods for Vocal Tract Nonnalization, " in Proc. of IEEE ICASSP, vol. 2, Phoenix, AZ, April 1 999, pp. 7 6 1-764.
24. M. Gerosa, D. Giuliani, and F. Brugnara, "Acoustic variability and automatic recognition of childrens speech, " Speech Communication, vol. 49, no. 1 0 1 1, pp. 847-860, 2007.
25. B. Angelini, F. Brugnara, D. Falavigna, D. Giuliani, R. Gretter, and M. Omologo, " Speaker Independent Continuous Speech Recognition Using an AcousticPhonetic Italian Corpus, " in Proc. ofICSLP, Yokohama, Japan, Sept. 1 994, pp. 1 3 9 1-1 3 94.
26. K. Vesely, L. Burget, and F. Grezl, "Parallel training of neural networks for speech recognition, " i n Text, Speech and Dialogue. Springer, 20 1 0, pp. 43 9-446.
27. G. Hinton, S. Osindero, and Y.-w. Teh, "A fast learning algorithm for deep belief nets, " Neural computation, vol. 1 8, no. 7, pp. 1 527-1 554, 2006.
28. D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, and S. Bengio, "Why does unsupervised pretraining help deep learning?" The Journal of Machine Learning Research, vol. I I, pp. 625-660, 20 1 0.
29. L. Gillick and S. Cox, " Some Statistical Issues in the Comparison of Speech Recognition Algorithms, " in Proc. of IEEE ICASSP, Glasgow, Scotland, May 1 989, pp. I-53 2-5 3 5.
30. A. Narayanan and D. Wang, "Joint noise adaptive training for robust automatic speech recognition, " in Proc. of IEEE ICASSP, 20 1 4, pp. 2523-2527.