| Paper: | SLP-P14.12 | ||
| Session: | Speaker Recognition: Models and Methods | ||
| Time: | Thursday, May 18, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Speaker Identification | ||
| Title: | Far-Field Speaker Recognition | ||
| Authors: | Qin Jin, Yue Pan, Tanja Schultz, Carnegie Mellon University, United States | ||
| Abstract: | In this paper we study robust speaker recognition in far-field microphone situations such as meeting senarios. By applying reverberation compensation and feature warping we achieved significant improvements under mismatched training-testing conditions. To capture useful information from multiple distant microphones, two approaches for multiple channel combination are investigated. This leads to 84.1%and 78.1% relative improvements on the Distant Microphone database. Furthermore, we tested the resulting system on the ICSI Meeting Corpus. The improvements are also very high on this task, which indicates that our system is robust to changing conditions in a remote microphone setting. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012