Concept information
Término preferido
synthetic voice
Definición
- A computer-generated or artificially created voice mimicking human speech that is generated by a speech synthesis system.
Concepto genérico
Etiquetas alternativas
- artificial speech
- artificial voice
- computer-generated speech
- computer-generated voice
- computer-synthesized speech
- computer-synthesized voice
- machine-generated speech
- machine-generated voice
- synthesized speech
- synthesized voice
- synthetic speech
Ejemplo
- A system called Text to Speech (TTS) converts text into artificial speech. (Gupta, 2023)
- Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. (Masson & Carson-berndsen, 2023)
- ESPnet was used for the acoustic model (60.6% WER) as Kaldi performances dramatically decreased integrating artificial speech in the training data (WER >90%). (Desot, Portet & Vacher, 2020)
- In order to build a synthetic voice it is necessary: to design a speech database that contains adequate phonetic and prosodic variation found within the language; record the data from a native speaker; construct a pronunciation lexicon; and build the synthetic voice itself. (Bach, Eck, Charoenpornsawat, Köhler, Stüker, Nguyen, Hsiao, Waibel, Vogel, Schultz & Black, 2007)
- Once the excitation signal Is obtained the synthetic speech Is generated by exciting the vocal tract system with the excitation samples. (Yegnanarayana, Naik & Childers, 1984)
En otras lenguas
-
francés
-
parole artificielle
-
parole de synthèse
-
parole électronique
-
parole synthétique
-
voix artificielle
-
voix synthétique
URI
http://data.loterre.fr/ark:/67375/8LP-ZSJPZPNH-N
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}