About: BINSEG: An Efficient Speaker-based Segmentation Technique

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

About: BINSEG: An Efficient Speaker-based Segmentation Technique 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 a new efficient approach to speaker-based audio stream segmentation. It employs binary segmentation technique that is well-known from mathematical statistic. Because integral part of this technique is hypotheses testing, we compare two well-founded (Maximum Likelihood, Informational) and one commonly used (BIC difference) approach for deriving speaker-change test statistics. Based on results of this comparison we propose both off-line and on-line speaker change detection algorithms (including way of effective training) that have merits of high accuracy and low computational costs. In simulated tests with artificially mixed data the on-line algorithm identified 95.7% of all speaker changes with precision of 96.9%. In tests done with 30 hours of real broadcast news (in 9 languages) the average recall was 74.4% and precision 70.3%. In this paper we present a new efficient approach to speaker-based audio stream segmentation. It employs binary segmentation technique that is well-known from mathematical statistic. Because integral part of this technique is hypotheses testing, we compare two well-founded (Maximum Likelihood, Informational) and one commonly used (BIC difference) approach for deriving speaker-change test statistics. Based on results of this comparison we propose both off-line and on-line speaker change detection algorithms (including way of effective training) that have merits of high accuracy and low computational costs. In simulated tests with artificially mixed data the on-line algorithm identified 95.7% of all speaker changes with precision of 96.9%. In tests done with 30 hours of real broadcast news (in 9 languages) the average recall was 74.4% and precision 70.3%. (en)
Title	BINSEG: An Efficient Speaker-based Segmentation Technique BINSEG: An Efficient Speaker-based Segmentation Technique (en)
skos:prefLabel	BINSEG: An Efficient Speaker-based Segmentation Technique BINSEG: An Efficient Speaker-based Segmentation Technique (en)
skos:notation	RIV/46747885:24220/06:#0001340!RIV10-AV0-24220___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(1QS108040569)
http://linked.open...vai/riv/dodaniDat	2010
http://linked.open...aciTvurceVysledku	Žďánský, Jindřich
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	466930
http://linked.open...ai/riv/idVysledku	RIV/46747885:24220/06:#0001340
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	speaker change detection (en)
http://linked.open.../riv/klicoveSlovo	speaker change detection
http://linked.open...ontrolniKodProRIV	[9C5563B3D361]
http://linked.open...v/mistoKonaniAkce	Pittsburgh, USA
http://linked.open...i/riv/mistoVydani	Pittsburgh, USA
http://linked.open...i/riv/nazevZdroje	INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING
http://linked.open...in/vavai/riv/obor	JC
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	1 (xsd:int)
http://linked.open...vavai/riv/projekt	Assistence, information and communication services based on advanced voice technology
http://linked.open...UplatneniVysledku	2006
http://linked.open...iv/tvurceVysledku	Žďánský, Jindřich
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2006-01-01 (xsd:date)
issn	1990-9772
number of pages	4 (xsd:int)
http://purl.org/ne...btex#hasPublisher	ISCA-INST SPEECH COMMUNICATION ASSOC, C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS, BAIXAS, F-66390, FRANCE
https://schema.org/isbn	978-1-60423-449-7
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