|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
| | ||
| Search | ||
| ||
2009 Seventh International Conference on Advances in Pattern Recognition
High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition
February 04-February 06
ISBN: 978-0-7695-3520-3
| ASCII Text | x | ||
| S. Thiyagarajan, V. Ramasubramanian, "High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition," Advances in Pattern Recognition, International Conference on, pp. 163-166, 2009 Seventh International Conference on Advances in Pattern Recognition, 2009. | |||
| BibTex | x | ||
| @article{ 10.1109/ICAPR.2009.87, author = {S. Thiyagarajan and V. Ramasubramanian}, title = {High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition}, journal ={Advances in Pattern Recognition, International Conference on}, volume = {0}, year = {2009}, isbn = {978-0-7695-3520-3}, pages = {163-166}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICAPR.2009.87}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Advances in Pattern Recognition, International Conference on TI - High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition SN - 978-0-7695-3520-3 SP163 EP166 A1 - S. Thiyagarajan, A1 - V. Ramasubramanian, PY - 2009 KW - Speaker-recognition KW - inter-session variability KW - session adaptation KW - on-line KW - unsupervised VL - 0 JA - Advances in Pattern Recognition, International Conference on ER - | |||
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICAPR.2009.87
We propose an on-line session-adaptation algorithm for making variable-text speaker-recognition systems robust to inter-session variability, by a continuous update of registered speakers' multiple templates from test utterances during actual usage of the system. The algorithm is set in a speaker-verification mode of operation and uses an enhanced verification step to ensure reliable selection of input utterances for template updation in an unsupervised way.
Index Terms:
Speaker-recognition, inter-session variability, session adaptation, on-line, unsupervised
Citation:
S. Thiyagarajan, V. Ramasubramanian, "High Performance On-line Session-adaptation for Handling Inter-session Speaker Variability in Variable-text Speaker-recognition," icapr, pp.163-166, 2009 Seventh International Conference on Advances in Pattern Recognition, 2009
Usage of this product signifies your acceptance of the Terms of Use.
