| Paper: | SP-P3.9 | ||
| Session: | Topics in Speaker and Langauge Recognition | ||
| Time: | Tuesday, May 18, 15:30 - 17:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech Processing: Speaker Recognition | ||
| Title: | IDENTIFYING IN-SET AND OUT-OF-SET SPEAKERS USING NEIGHBORHOOD INFORMATION | ||
| Authors: | Pongtep Angkititrakul; University of Colorado, Boulder | ||
| John H. L. Hansen; University of Colorado, Boulder | |||
| Abstract: | In this paper we study the problem of identifying in-set and out-of-set speakers. The goal is to identify whether an unknown input speaker belongs to either a group of in-set speaker or an unseen out-of-set group. A state-of-the-art GMM classifier with Universal Background Model (UBM), and standard likelihood ratio test are used as our baseline system. We propose an alternative hypothesis testing method that employs neighborhood information with respect to each in-set speaker model in the model space based on the Kullback-Leibler divergence. The Bayes Factor is used in the verification stage (accept/reject hypothesis). We evaluate the proposed procedure on a clean CORPUS1 set, and a noisy CORPUS2 set which contains session-to-session variability.Experiments show an improvement in Equal Error Rate for the system even when in-set speaker models are acoustically close in the model space, and as the in-set speaker size increases. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops