Název:	Reducing footprint of unit selection TTS system by excluding utterances from source speech corpus
Další názvy:	Snižování paměťových nároků systému TTS pracujícího na principu výběru jednotek vyhozením promluv ze zdrojového řečového korpusu
Autoři:	Matoušek, Jindřich Tihelka, Daniel Hanzlíček, Zdeněk
Citace zdrojového dokumentu:	MATOUŠEK, Jindřich; TIHELKA, Daniel; HANZLÍČEK, Zdeněk. Reducing footprint of unit selection TTS system by excluding utterances from source speech corpus. In: Speech processing 19th czech – german workshop 29th September – 1st October 2009. Prague: Institute of Photonics and Electronics Academy of Sciences of the Czech Republic, 2009, p. 92-98. ISBN 978-80-86269-18-4.
Datum vydání:	2009
Nakladatel:	Institute of Photonics and Electronics Academy of Sciences of the Czech Republic
Typ dokumentu:	článek article
URI:	http://www.kky.zcu.cz/cs/publications/MatousekJ_2009_ReducingFootprintof http://hdl.handle.net/11025/17017
ISBN:	978-80-86269-18-4
Klíčová slova:	syntéza řeči;výběr jednotky;korpus řeči
Klíčová slova v dalším jazyce:	speech synthesis;unit selection;speech corpus
Abstrakt v dalším jazyce:	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 "slightly worse" than speech generated by the baseline (i.e. not reduced) system.
Práva:	© Jindřich Matoušek - Daniel Tihelka - Zdeněk Hanzlíček
Vyskytuje se v kolekcích:	Články / Articles (NTIS) Články / Articles (KIV)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.