A hierarchical system for word discovery exploiting DTW-based initialization

2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Volumn , Issue , 2013, Pages 386-391

  Walter, Oliver ^a   Korthals, Timo ^a   Haeb Umbach, Reinhold ^a   Raj, Bhiksha ^b  

^a UNIVERSITY OF PADERBORN   (Germany)

^b Carnegie Mellon University ^*  (United States)

Author keywords

acoustic units; Unsupervised; word discovery

Indexed keywords

CLASSIFICATION ERRORS; DYNAMIC TIME WARPING; EMISSION PROBABILITIES; HIERARCHICAL APPROACH; LINGUISTIC STRUCTURE; UNSUPERVISED; WORD DISCOVERIES; WORD PRONUNCIATION;

HIDDEN MARKOV MODELS; HIERARCHICAL SYSTEMS;

SPEECH RECOGNITION;

EID: 84893673786     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2013.6707761     Document Type: Conference Paper

References (14)

1. A. Jansen et al., "A summary of the 2012 JHU CLSP workshop on zero resource speech rechnologies and models of early language acquisition, " in Proc. ICASSP, Vancouver, Ca., May 2013.
2. A. Jansen and K. Church, "Towards unsupervised training of speaker independent acoustic models, " in Proc. Interspeech, Florence, Italy, 2011.
3. M. Siu, H. Gish, A. Chan, W. Belfield, and S. Lowe, "Unsupervised training of an HMM-based self-organiing unit recognizer with applications to topic classification and keyword discovery, " Comput. Speech Lang., 2013.
4. A. Jansen and H. Hermansky, "Weak top-down constraints for unsupervised acoustic model training, " in Proc. ICASSP, Vancouver, Ca., May 2013.
5. Daichi Mochihashi, Takeshi Yamada, and Naonori Ueda, "Bayesian unsupervised word segmentation with nested pitman-yor language modeling, " in Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1-Volume 1. Association for Computational Linguistics, 2009, pp. 100-108.
6. A. S. Park and James R. Glass, "Unsupervised pattern discovery in speech, " IEEE Transactions on Audio, Speech & Language Processing, vol. 16, no. 1, pp. 186-197, 2008.
7. Xavier Anguera, Robert Macrae, and Nuria Oliver, "Partial sequence matching using an unbounded dynamic time warping algorithm, " in Int. Conf. on Acoustics Speech and Signal Processing (ICASSP), 2010.
8. Sourish Chaudhuri and Bhiksha Raj, "Unsupervised structure discovery for semantic analysis of audio, " in Advances in Neural Information Processing Systems 25, 2012, pp. 1187-1195.
9. Sourish Chaudhuri, Mark Harvilla, and Bhiksha Raj, "Unsupervised learning of acoustic unit descriptors for audio content representation and classification, " in INTERSPEECH. 2011, pp. 2265-2268, ISCA.
10. Joerg Schmalenstroeer, Markus Bartek, and Reinhold Haeb- Umbach, "Unsupervised learning of acoustic events using dynamic time warping and hierarchical k-means++ clustering, " in Interspeech 2011, 2011.
11. David Arthur and Sergei Vassilvitskii, "k-means++: The advantages of careful seeding, " in Proc. ACM-SIAM symposium on Discrete algorithms, 2007, pp. 1027-1035.
12. M. E. J. Newman and M. Girvan, "Finding and evaluating community structure in networks, " Physical Review E, vol. 69, no. 2, pp. 026113+, Feb. 2004.
13. Christopher D Manning and Hinrich Schütze, Foundations of statistical natural language processing, MIT press, 1999.
14. Michael A Carlin, Samuel Thomas, Aren Jansen, and Hynek Hermansky, "Rapid evaluation of speech representations for spoken term discovery., " in INTERSPEECH, 2011, pp. 821- 824.