Learning speaker-specific characteristics with a deep neural architecture

IEEE Transactions on Neural Networks

Volumn 22, Issue 11, 2011, Pages 1744-1756

  Chen, Ke ^a   Salman, Ahmad ^a  

^a UNIVERSITY OF MANCHESTER   (United Kingdom)

Author keywords

Deep neural architecture; hybrid learning strategy; overcomplete representation; speaker comparison; speaker segmentation; speaker verification; speaker specific characteristics

Indexed keywords

HYBRID LEARNING; NEURAL ARCHITECTURES; OVERCOMPLETE REPRESENTATIONS; SPEAKER COMPARISON; SPEAKER SEGMENTATIONS; SPEAKER VERIFICATION; SPEAKER-SPECIFIC CHARACTERISTICS;

ARCHITECTURE; LINGUISTICS; NETWORK ARCHITECTURE; NEURAL NETWORKS; SPEECH PROCESSING;

SPEECH RECOGNITION;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; AUTOMATIC SPEECH RECOGNITION; BIOLOGICAL MODEL; COMPUTER SYSTEM; DISCRIMINATION LEARNING; HUMAN; LANGUAGE; NORMAL DISTRIBUTION;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTER SYSTEMS; DISCRIMINATION LEARNING; HUMANS; LANGUAGE; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION; SPEECH RECOGNITION SOFTWARE;

EID: 80455143732     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2011.2167240     Document Type: Article

References (41)

1. J. Campbell, "Speaker recognition: A tutorial," IEEE Proc., vol. 85, no. 8, pp. 1437-1462, Sep. 1997.
2. J. P. Campbell, W. Shen, W. M. Campbell, R. Schwartz, J. F. Bonastre, and D. Matrouf, "Forensic speaker recognition," IEEE Signal Proc. Mag., vol. 26, no. 2, pp. 95-103, Mar. 2009.
3. X. Huang, A. Acero, and H. Hon, Spoken Language Processing. Englewood Cliffs, NJ: Prentice Hall, 2001.
4. Q. Jin, "Robust speaker recognition," Ph.D. thesis, School Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, 2007.
5. R. Mammone, X. Zhang, and R. Ramachandran, "Robust speaker recognition: A feature-based approach," IEEE Signal Process. Mag., vol. 13, no. 5, pp. 1-58, Sep. 1996.
6. D. A. Reynolds, "Speaker Identification and verification using Gaussian mixture speaker models," Speech Commun., vol. 17, nos. 1-2, pp. 91-108, Aug. 1995.
7. D. A. Reynolds, "Speaker Identification and verification using Gaussian mixture speaker models," MIT Lincoln Lab. J., vol. 8, pp. 173-191, Jan. 1995.
8. S. Kajarekar, "Analysis of variability in speech with applications to speech and speaker recognition," Ph.D. thesis, School Sci. Eng., Oregon Graduate Institute Sci. Eng., Portland, OR, 2002.
9. V. Laparra, G. Camps-Valls, and J. Malo, "Iterative gaussianization: From ICA to random rotations," IEEE Trans. Neural Netw., vol. 22, no. 4, pp. 537-549, Apr. 2011.
10. Y. Bengio and Y. LeCun, "Scaling learning algorithms toward AI," in Large Scale Kernel Machine. Cambridge, MA: MIT Press, 2007, pp. 321-360.
11. Y. Bengio, "Learning deep architectures for AI," Foundations Trends Mach. Learn., vol. 2, no. 1, pp. 1-127, 2009.
12. G. E. Hinton, "Learning multiple layers of representation," Trends Cogn. Sci., vol. 11, no. 10, pp. 428-434, Oct. 2007.
13. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, Jul. 2006.
14. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient based learning applied to document recognition," IEEE Proc., vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
15. G. E. Hinton, S. Osindero, and Y. W. Teh, "A fast learning algorithm for deep belief nets," Neural Comput., vol. 18, no. 7, pp. 1527-1554, Jul. 2006.
16. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy layerwise training of deep networks," in Proc. Adv. Neural Inform. Process. Syst., vol. 19. 2007, pp. 1-8.
17. K. Jarrett, K. Kavukcuoglu, M. Ranzato, and Y. LeCun, "What is the best multi-stage architecture for object recognition?," in Proc. IEEE 12th Int. Conf. Comput. Vision, Kyoto, Japan, Sep.-Oct. 2009, pp. 2146-2153.
18. H. Larochelle, Y. Bengio, J. Louradour, and P. Lamblin, "Exploring strategies for training deep neural networks," J. Mach. Learn. Res., vol. 10, pp. 1-40, Jan. 2009.
19. D. Erhan, Y. Bengio, A. Courville, P. Manzagol, and P. Vincent, "Why does unsupervised pre-training help deep learning?," J. Mach. Learn. Res., vol. 11, pp. 625-660, Feb. 2010.
20. R. Salakhutdinov and G. Hinton, "Learning a non-linear embedding by preserving class neighbourhood structure," in Proc. Art. Intell. Statis., vol. 2. 2007, pp. 412-419.
21. M. Osadchy, Y. LeCun, and M. Miller, "Synergistic face detection and pose estimation with energy-based models," J.Mach. Learn. Res., vol. 8, pp. 1197-1215, May 2007.
22. S. Chopra, R. Hadsell, and Y. LeCun, "Learning a similarity metric discriminatively, with application to face verification," in Proc. IEEE Computr. Soc. Conf. Comput. Vision Pattern Recognit., vol. 1. Jun. 2005, pp. 539-546.
23. Y. LeCun, F. J. Huang, and L. Bottou, "Learning methods for generic object recognition with invariance to pose and lighting," in Proc. IEEE Computr. Soc. Conf. Comput. Vision Pattern Recognit., vol. 2. Jul. 2004, pp. 97-104.
24. H. Larochelle, D. Erhan, A. Courville, J. Bergstra, and Y. Bengio, "An empirical evaluation of deep architectures on problems with many factors of variation," in Proc. 24th Int. Conf. Mach. Learn., 2007, pp. 473-480.
25. H. Lee, Y. Largman, P. Pham, and A. Y. Ng, "Unsupervised feature learning for audio classification using convolutional deep belief networks," in Proc. Adv. Neural Informat. Process. Syst., vol. 22. 2010, pp. 1-9.
26. Linguistic Data Consortium (LDC), Philadelphia, PA [Online]. Available: http://www.ldc.upenn.edu.com
27. Russian Speech Corpus [Online]. Available: http://www.repository. voxforge1.org/
28. L. Wang, "Chinese speech corpus for speaker recognition," Shenzhen Inst. Advanced Technology, Chinese Academy Science, Shenzhen, China, Tech. Rep., pp. 1-66, 2008.
29. Y. LeCun and F. J. Huang, "Loss functions for discriminative training of energy-based models," in Proc. Art. Intell. Statist., 2005, pp. 1-8.
30. J. Bromley, I. Guyon, Y. LeCun, E. Sackinger, and R. Shah, "Signature verification using a siamese time delay neural network," in Proc. Adv. Neural Inform. Process. Syst., vol. 5. 1993, pp. 1-3.
31. K. Chen, "Toward better making a decision in speaker verification," Pattern Recog., vol. 36, no. 2, pp. 329-346, Feb. 2003.
32. L. Wang, K. Chen, and H. Chi, "Capture inter-speaker information with a neural network for speaker identification," IEEE Trans. Neural Netw., vol. 13, no. 2, pp. 436-445, Mar. 2002.
33. P. Vincent, H. Larochelle, Y. Bengio, and P. Manzagol, "Extracting and composing robust features with denoising autoencoders," in Proc. Art. Intell. Statis., 2007, pp. 1-8.
34. W. Campbell, D. E. Sturim, and Z. Karam, "Speaker comparison with inner product discriminant functions," in Proc. Adv. Neural Inform. Process. Syst., vol. 22. 2010, pp. 1-9.
35. D. A. Reynolds and R. C. Rose, "Robust text-independent speaker identification using Gaussian mixture speaker models," IEEE Trans. Speech Audio Process., vol. 3, no. 1, pp. 72-83, Jan. 1995.
36. A. Martin, G. Doddington, T. Kamm, M. Ordowski, and M. Pryzbocki, "The DET curve in assessment of detection task performance," in Proc. Eurospeech, vol. 4. 1997, pp. 1899-1903.
37. S. Zhang and M. Mak, "Optimized discriminative kernel for SVM scoring and its application to speaker verification," IEEE Trans. Neural Netw., vol. 22, no. 2, pp. 173-185, Feb. 2011.
38. M. Kotti, V. Moschou, and C. Kotropoulos, "Speaker segmentation and clustering," Signal Process., vol. 88, no. 5, pp. 1091-1124, May 2008.
39. P. Delacourt and C. Wellekens, "DISTBIC: A speaker-based segmentation for audio data indexing," Speech Commun., vol. 32, nos. 1-2, pp. 111-126, Sep. 2000.
40. S. S. Chen and P. S. Gopalakrishnan, "Speaker environment and channel change detection and clustering via Bayesian information criterion," in Proc. Defense Adv. Res. Projects Agency Speech Recognit. Workshop, 1998, pp. 127-132.
41. J. Goldberger, S. Roweis, G. Hinton, and R. Salakhutdinov, "Neighbourhood component analysis," in Proc. Adv. Neural Inform. Process. Syst., vol. 17. 2005, pp. 1-8.