About: On modelling syllables in text-to-speech synthesis     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)

AttributesValues
rdf:type
Description
  • V tomto článku ukazujeme možnosti využití slabik jako alternativních akustických jednotek k fonémům v úloze syntézy řeči z textu. Navrhujeme, realizujeme a vyhodnocujeme několik možností modelování slabik v rámci statistického přístupu k vytváření inventáře řečových jednotek (s využitím HMM). Abychom bylo možné syntetizovat libovolný text, inventář musel být rozšířen o trifóny; výsledkem je hybridní slabiko-trifónový inventář. Nejprve jsme uvažovali slabiky jako kontextově nezávislé, vycházeje z předpokladu, že nejsilnější koartikulace je uzavřena právě uvnitř slabiky. Dále jsme zkusili modelovat slabiky včetně kontextu, jelikož ale není možné brát jednotliv (cs)
  • In this paper, an attempt to use syllables as alternative acoustic units to phones in text-to-speech tasks is presented. We proposed, examined and evaluated several options of syllable modelling within the scope of the statistical approach (using HMMs) to the acoustic unit inventory creation. To be able to synthesize an arbitrary text, the inventory has to be extended with triphones, resulting in a hybrid syllable/triphone inventory. First, we did not reflect the phonetic contexts of the syllables, because we supposed that the most of co-articulation is included inside syllables. Next, we also tried to model the context-dependent syllables. However, it is not viable to take each individual phone as a context. Therefore, each context was formed by a group of acoustically similar phones. Several listening tests were performed to rate the quality of the resulting synthetic speech.
  • In this paper, an attempt to use syllables as alternative acoustic units to phones in text-to-speech tasks is presented. We proposed, examined and evaluated several options of syllable modelling within the scope of the statistical approach (using HMMs) to the acoustic unit inventory creation. To be able to synthesize an arbitrary text, the inventory has to be extended with triphones, resulting in a hybrid syllable/triphone inventory. First, we did not reflect the phonetic contexts of the syllables, because we supposed that the most of co-articulation is included inside syllables. Next, we also tried to model the context-dependent syllables. However, it is not viable to take each individual phone as a context. Therefore, each context was formed by a group of acoustically similar phones. Several listening tests were performed to rate the quality of the resulting synthetic speech. (en)
Title
  • On modelling syllables in text-to-speech synthesis
  • Modelování slabik v syntéze řeči z textu (cs)
  • On modelling syllables in text-to-speech synthesis (en)
skos:prefLabel
  • On modelling syllables in text-to-speech synthesis
  • Modelování slabik v syntéze řeči z textu (cs)
  • On modelling syllables in text-to-speech synthesis (en)
skos:notation
  • RIV/49777513:23520/05:00000035!RIV07-AV0-23520___
http://linked.open.../vavai/riv/strany
  • 438
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(1ET101470416)
http://linked.open...iv/cisloPeriodika
  • 0
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 534371
http://linked.open...ai/riv/idVysledku
  • RIV/49777513:23520/05:00000035
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • syllables; syllabification; text-to-speech; speech synthesis; HMM; hybrid AUI; artificial intelligence (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...odStatuVydavatele
  • DE - Spolková republika Německo
http://linked.open...ontrolniKodProRIV
  • [971FC1FC5B1A]
http://linked.open...i/riv/nazevZdroje
  • Studientexte zur Sprachkommunikation
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Hanzlíček, Zdeněk
  • Matoušek, Jindřich
  • Tihelka, Daniel
issn
  • 0940-6832
number of pages
http://localhost/t...ganizacniJednotka
  • 23520
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
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, 48 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software