Skip Navigation

IEICE Transactions on Information and Systems 2007 E90-D(4):759-765; doi:10.1093/ietisy/e90-d.4.759
This Article
Right arrow Full Text (PDF)
Right arrow References
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrow Request Permissions
Google Scholar
Right arrow Articles by SAETA, J. R.
Right arrow Articles by HERNANDO, J.
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

Copyright © 2007 The Institute of Electronics, Information and Communication Engineers

Regular Section -- Papers -- Speech and Hearing

Assessment of On-Line Model Quality and Threshold Estimation in Speaker Verification

Javier R. SAETA1 and Javier HERNANDO2

1 The author is with Biometric Technologies, S.L., Barcelona, 08007 Spain., 2 The author is with TALP Research Center (UPC), Barcelona, 08034 Spain. E-mail: javier{at}gps.tsc.upc.es


  Abstract

The selection of the most representative utterances coming from a speaker is essential for the right performance of automatic enrollment in speaker verification. Model quality measures and threshold estimation methods mainly deal with the scarcity of data and the difficulty of obtaining data from impostors in real applications. Conventional methods estimate the quality of the training utterances once the model is created. In such case, it is not possible to ask the user for more utterances during the training session if necessary. A new training session must be started. That was especially unusable in applications where only one or two enrolment sessions were allowed. In this paper, a new on-line quality method based on a male and a female Universal Background Model (UBM) is introduced. The two models act as a reference for new utterances and show if they belong to the same speaker and provide a measure of its quality at the same time. On the other hand, the estimation of the verification threshold is also strongly influenced by the previous selection of the speaker's utterances. In this context, potential outliers, i.e., those client scores which are distant with regard to mean, could lead to wrong mean and variance client estimations. To alleviate this problem, some efficient threshold estimation methods based on removing or weighting scores are proposed here. Before estimating the threshold, the client scores catalogued as outliers are removed, pruned or weighted, improving subsequent estimations. Text-dependent experiments have been carried out by using a telephonic multi-session database in Spanish. The database has been recorded by the authors and has 184 speakers.

Key Words: speaker verification, threshold, quality, model estimation, pruning

Manuscript received January 17, 2005. Manuscript revised June 3, 2005.


Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?




Disclaimer:
Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.