Název:	T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion
Autoři:	Řezáčková, Markéta Švec, Jan Tihelka, Daniel
Citace zdrojového dokumentu:	ŘEZÁČKOVÁ, M. ŠVEC, J. TIHELKA, D. T5G2P: Using Text-to-Text Transfer Transformer for Grapheme-to-Phoneme Conversion. In Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech. Red Hook, NY: International Speech Communication Association, 2021. s. 3291-3295. ISBN: 978-1-71383-690-2 , ISSN: 2308-457X
Datum vydání:	2021
Nakladatel:	International Speech Communication Association
Typ dokumentu:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85115262876 http://hdl.handle.net/11025/47249
ISBN:	978-1-71383-690-2
ISSN:	2308-457X
Klíčová slova v dalším jazyce:	grapheme-to-phoneme;phonetic transcription;T5;transformers;TTS system
Abstrakt v dalším jazyce:	Despite the increasing popularity of end-to-end text-to-speech (TTS) systems, the correct grapheme-to-phoneme (G2P) module is still a crucial part of those relying on a phonetic input. In this paper, we, therefore, introduce a T5G2P model, a Text-to-Text Transfer Transformer (T5) neural network model which is able to convert an input text sentence into a phoneme sequence with a high accuracy. The evaluation of our trained T5 model is carried out on English and Czech, since there are different specific properties of G2P, including homograph disambiguation, cross-word assimilation and irregular pronunciation of loanwords. The paper also contains an analysis of a homographs issue in English and offers another approach to Czech phonetic transcription using the detection of pronunciation exceptions.
Práva:	Plný text není přístupný. © ISCA
Vyskytuje se v kolekcích:	Konferenční příspěvky / Conference Papers (KKY) OBD

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