Data Driven Grapheme-to-Phoneme Representations for a Lexicon-Free Text-to-Speech

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, us...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 11091 - 11095
Hlavní autori: Garg, Abhinav, Kim, Jiyeon, Khyalia, Sushil, Kim, Chanwoo, Gowda, Dhananjaya
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 14.04.2024
Predmet:
Acoustics
data-driven G2P
Grapheme-to-Phoneme
lexicon-free TTS
Linguistics
Self-supervised learning
Signal processing
Speech processing
Text-to-Speech
ISSN:2379-190X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem. Firstly, the lexicons are generated using a fixed phoneme set, usually, ARPABET or IPA, which might not be the most optimal way to represent phonemes for all languages. Secondly, the man-hours required to produce such an expert lexicon are very high. In this paper, we eliminate both of these issues by using recent advances in self-supervised learning to obtain data-driven phoneme representations instead of fixed representations. We compare our lexicon-free approach against strong baselines that utilize a well-crafted lexicon. Furthermore, we show that our data-driven lexicon-free method performs as good or even marginally better than the conventional rule-based or lexicon-based neural G2Ps in terms of Mean Opinion Score (MOS) while using no prior language lexicon or phoneme set, i.e. no linguistic expertise.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10446275