Towards robust word discovery by self-similarity matrix comparison

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2011, Pages 5640-5643

  Muscariello, Armando ^a   Gravier, Guillaume ^a   Bimbot, Frédéric ^a  

^a CAMPUS DE BEAULIEU   (France)

Author keywords

dynamic programming; histogram of oriented gradients; unsupervised learning; word discovery

Indexed keywords

BROADCAST NEWS; DISSIMILARITY MEASURES; DYNAMIC TIME WARPING; HISTOGRAM OF ORIENTED GRADIENTS; LINGUISTIC KNOWLEDGE; PATTERN RECOGNITION TECHNIQUES; SELF-SIMILARITIES; SELF-SIMILARITY MATRIX; SPEECH SEQUENCES; SPOKEN DOCUMENT; TRAINING DATA; TRAINING MATERIAL; WORD DISCOVERY;

DYNAMIC PROGRAMMING; PATTERN MATCHING; SIGNAL PROCESSING; SPEECH RECOGNITION;

SPEECH COMMUNICATION;

EID: 80051628255     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2011.5947639     Document Type: Conference Paper

References (8)

1. A. Muscariello, G. Gravier, and F. Bimbot, "Audio keyword extraction by unsupervised word discovery", in Interspeech. ISCA, 2009, pp. 2843-2846.
2. X. Zhu, G. Penn and F. Rudzicz, "Summarizing multiple spoken documents: finding evidence from untranscribed audio", in Proceedings of the 47th annual meeting of the ACL and the 4th IJCNLP and of the AFNLP, 2009, 549-557.
3. A. Jansen, K. Church and H. Hermansky, " Towards spoken term discovery at scale with zero resources", in Interspeech. ISCA, 2010, pp. 1676-1679.
4. Y. Zhang and J. Glass, "Towards multi-speaker unsupervised speech patterns discovery", in ICASSP. IEEE, 2010.
5. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection", in CVPR. IEEE, 2005, pp 886-893.
6. M. Dredze, A. Jansen, G. Coppersmith and K. Church "NLP on Spoken Documents without ASR", in EMNLP, 2010.
7. C. Herley "Automatically extracting repeating objects frommultimedia streams", Transactions onMultimedia, IEEE, vol. 8, pp. 115-129, February 2006.
8. A. Muscariello, G Gravier and F. Bimbot "Variability tolerant audio motif discovery", in Multimedia Modeling, 2009.