Back to Results
First PageMeta Content
Automatic identification and data capture / Science / Computational linguistics / Speaker diarisation / Speech recognition / Natural language processing / Segmentation / Speaker recognition / Beamforming / Speech processing / Statistics / Human–computer interaction


FIRST DRAFT SUBMITTED TO IEEE TASLP: 19 AUGUSTSpeaker Diarization: A Review of Recent Research Xavier Anguera, Member, IEEE, Simon Bozonnet, Student Member, IEEE, Nicholas Evans, Member, IEEE,
Add to Reading List

Document Date: 2012-01-09 06:31:58


Open Document

File Size: 1,00 MB

Share Result on Facebook

Company

GPU / DER / Fisher LDA / Telefonica / /

/

Event

Reorganization / /

Facility

National Institute of Standards and Technology / University of Avignon / US National Institute / University of California at Berkeley / /

IndustryTerm

mono-channel diarization systems / by-product / Bottom-up systems / dynamic output signal weighting algorithm / present state-of-the-art systems / parametric systems / telephone speech / state-ofthe-art systems / bottom-up diarization algorithms / room recording equipment / telephony domain / potential solution / delay-and-sum algorithm / speaker diarization algorithms / variable energy levels / harmonic energy ratio / potential solutions / present state-of-the-art speaker diarization systems / speech activity detection algorithm / dynamic programming algorithm / source localization algorithms / speaker segmentation algorithms / live speaker diarization systems / telephony data / cluster initialization algorithms / energy / diarization systems / axis merging algorithm / pre-processing step / faster algorithms / topdown algorithms / upstream processing step / belief network / technology dates / present diarization systems / adaptive algorithms / important key technology / it difficult to assess novel algorithms / individual systems / real-time processing / energy-based detector / appropriate tracking algorithms / telephone conversations / nonparametric systems / speech processing applications / speech processing / speech processing research / speaker diarization systems / data-driven learning algorithm / video document processing / speech algorithms / diarization algorithms / multimodal technologies / satellite microphone / human-to-human communications / data purification algorithms / experimental protocols / stateof-the-art systems / /

MarketIndex

NIST RT / /

Organization

University of California / US National Institute for Standards and Technology / NIST RT / National Institute of Standards and Technology / ICSI / European Union / University of Avignon / VT EDI / /

Person

Simon Bozonnet / Mel Frequency Cepstrum Coefficients / Gerald Friedland / Corinne Fredouille / Nicholas Evans / Xavier Anguera / AMI CMU ICSI NIST VT / Transcription / /

Position

model of each segment / active speaker / so-called speaker / Speaker / THE AVERAGE SPEAKER / RT / See http /

Product

M-16 / /

Technology

speech activity detection algorithm / speech recognition / Av / dynamic output signal weighting algorithm / performing frame assignment using Viterbi algorithm / Viterbi algorithm / two axis merging algorithm / diarization algorithms / hybridization / speech algorithms / scoring algorithm / previous cluster initialization algorithms / data-driven learning algorithm / machine learning / delay-and-sum algorithm / speaker segmentation algorithms / bottom-up diarization algorithms / data purification algorithms / speaker diarization algorithms / main algorithms / important key technology / alternative beamforming algorithms / meetings diarization algorithms / appropriate tracking algorithms / source localization algorithms / dynamic programming algorithm / adaptive algorithms / 2010 algorithm / /

URL

http /

SocialTag