Back to Results
First PageMeta Content
Human communication / Computational linguistics / Science / Phonetics / Speech / Speech recognition / Mel-frequency cepstrum / Speech error / Linear predictive coding / Automatic identification and data capture / Speech processing / Human–computer interaction


OVERLAPPED SPEECH DETECTION FOR IMPROVED SPEAKER DIARIZATION IN MULTIPARTY MEETINGS Kofi Boakye1 , Beatriz Trueba-Hornero1,2 , Oriol Vinyals1 , Gerald Friedland1 1 International Computer Science Institute, Berkeley, CA,
Add to Reading List

Document Date: 2008-02-06 14:48:44

Open Document

File Size: 57,57 KB

Share Result on Facebook

City

Toulouse / Baltimore / Multimedia / Aalborg / /

Company

ACM Press / /

Country

France / United States / Denmark / /

Facility

Polytechnic University of Catalonia / International Computer Science Institute / /

IndustryTerm

higher energy content / post-processing step / diarization systems / channel energy estimates / residual energy / overlap-detecting diarization systems / residual energy values / post-processing procedure / automatic processing / segment post-processing procedure / post-processing / diarization pre-processing step / speaker diarization systems / energy content / post-processing speaker assignment algorithm / energy / /

Organization

Polytechnic University of Catalonia / Barcelona / International Computer Science Institute / IM2 / European Union / Swiss National Science Foundation / /

Position

scoring speaker / automatic speaker / speaker / RT / additional speaker / IMPROVED SPEAKER / /

ProgrammingLanguage

LPC / /

ProvinceOrState

Maryland / New York / /

Technology

speech recognition / sliding windows / post-processing speaker assignment algorithm / /

SocialTag