About: Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
Description	In this paper we present our system for speaker diarization of broadcast news based on recent advances in the speaker recognition field. In the system, speaker segments determined by the speaker changepoint detector are represented by i-vectors and similarity of segments’ speakers evaluated using cosine distance scoring. Linear discriminant analysis is employed to cope with intra-speaker variability. The experiments were carried out using the COST278 multilingual broadcast news database. We demonstrate improvement of the performance over the baseline system based on the Bayesian Information Criterion (BIC) and highlight significant impact of cepstral mean normalization. Finally, two-stage clustering employing BIC-based clustering to pre-cluster segments in the first stage is examined and showed to yield further performance improvement. The best performing configuration of our system achieved 52.4 % relative improvement of the speaker error rate over the baseline. In this paper we present our system for speaker diarization of broadcast news based on recent advances in the speaker recognition field. In the system, speaker segments determined by the speaker changepoint detector are represented by i-vectors and similarity of segments’ speakers evaluated using cosine distance scoring. Linear discriminant analysis is employed to cope with intra-speaker variability. The experiments were carried out using the COST278 multilingual broadcast news database. We demonstrate improvement of the performance over the baseline system based on the Bayesian Information Criterion (BIC) and highlight significant impact of cepstral mean normalization. Finally, two-stage clustering employing BIC-based clustering to pre-cluster segments in the first stage is examined and showed to yield further performance improvement. The best performing configuration of our system achieved 52.4 % relative improvement of the speaker error rate over the baseline. (en)
Title	Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring (en)
skos:prefLabel	Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring Speaker Diarization of Broadcast Streams using Two-stage Clustering based on I-vectors and Cosine Distance Scoring (en)
skos:notation	RIV/46747885:24220/12:#0002004!RIV13-TA0-24220___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(TA01011204)
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Pražák, Jan Silovský, Jan
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Technická univerzita v Liberci / Fakulta mechatroniky, informatiky a mezioborových studií
http://linked.open...dnocenehoVysledku	170198
http://linked.open...ai/riv/idVysledku	RIV/46747885:24220/12:#0002004
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	speaker diarization; broadcast news; clustering; i-vectors (en)
http://linked.open.../riv/klicoveSlovo	clustering i-vectors broadcast news speaker diarization
http://linked.open...ontrolniKodProRIV	[BECE5495B368]
http://linked.open...v/mistoKonaniAkce	Tokyo, Japonsko
http://linked.open...i/riv/mistoVydani	Japonsko
http://linked.open...i/riv/nazevZdroje	Proc. of International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2012
http://linked.open...in/vavai/riv/obor	JC
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	Living Archives
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Pražák, Jan Silovský, Jan
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open...ain/vavai/riv/wos	000312381404066
http://linked.open.../riv/zahajeniAkce	2012-01-01 (xsd:date)
number of pages	4 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Neuveden
https://schema.org/isbn	978-1-4673-0046-9
http://localhost/t...ganizacniJednotka	24220

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software