About: Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus

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

About: Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus Goto Sponge Distinct 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	Current unit selection speech synthesis systems are capable of producing speech of a high quality at the expense of enormous computational and storage requirements. In this paper, the analysis of an existing large speech corpus employed for unit-selection-based synthesis of Czech speech is performed. Subsequently, a procedure for the exclusion of some amount of utterances from the source speech corpus is proposed. The procedure is based on the statistics of the utilisation of all utterances during text-to-speech synthesis of a large portion of texts. The exclusion of whole utterances was preferred over the exclusion of the particular instances of speech units in order to preserve the main feature of unit selection framework - to select as longest sequence of contiguous speech units as possible. After the exclusion, the footprint of the system was reduced approximately by 42 %. The resulting synthetic speech was then judged by means of 5-scale CCR listening tests and evaluated in average as only Current unit selection speech synthesis systems are capable of producing speech of a high quality at the expense of enormous computational and storage requirements. In this paper, the analysis of an existing large speech corpus employed for unit-selection-based synthesis of Czech speech is performed. Subsequently, a procedure for the exclusion of some amount of utterances from the source speech corpus is proposed. The procedure is based on the statistics of the utilisation of all utterances during text-to-speech synthesis of a large portion of texts. The exclusion of whole utterances was preferred over the exclusion of the particular instances of speech units in order to preserve the main feature of unit selection framework - to select as longest sequence of contiguous speech units as possible. After the exclusion, the footprint of the system was reduced approximately by 42 %. The resulting synthetic speech was then judged by means of 5-scale CCR listening tests and evaluated in average as only (en)
Title	Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus (en)
skos:prefLabel	Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus (en)
skos:notation	RIV/49777513:23520/09:00504529!RIV11-GA0-23520___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(2C06020), P(GA102/09/0989)
http://linked.open...vai/riv/dodaniDat	2011
http://linked.open...aciTvurceVysledku	Tihelka, Daniel Matoušek, Jindřich Hanzlíček, Zdeněk
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	Západočeská univerzita v Plzni / Fakulta aplikovaných věd
http://linked.open...dnocenehoVysledku	338442
http://linked.open...ai/riv/idVysledku	RIV/49777513:23520/09:00504529
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	speech synthesis; unit selection; footprint reduction (en)
http://linked.open.../riv/klicoveSlovo	speech synthesis unit selection footprint reduction
http://linked.open...ontrolniKodProRIV	[5FA38FBC9E69]
http://linked.open...v/mistoKonaniAkce	Prague
http://linked.open...i/riv/mistoVydani	Prague
http://linked.open...i/riv/nazevZdroje	Speech Processing
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	Elimination of the language barriers faced by the handicapped watchers of the Czech Television New innovative methods for high-quality synthesis of Czech speech
http://linked.open...UplatneniVysledku	2009
http://linked.open...iv/tvurceVysledku	Hanzlíček, Zdeněk Matoušek, Jindřich Tihelka, Daniel
http://linked.open...vavai/riv/typAkce	EUR - Evropská
http://linked.open.../riv/zahajeniAkce	2009-01-01 (xsd:date)
number of pages	8 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Ústav fotoniky a elektroniky AV ČR
https://schema.org/isbn	978-80-86269-18-4
http://localhost/t...ganizacniJednotka	23520
is http://linked.open...avai/riv/vysledek of	Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus Reducing Footprint of Unit Selection TTS System by Excluding Utterances from Source Speech Corpus

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, 85 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software