A Language Modeling Approach to Diacritic-Free Hebrew TTS
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914874756431872 |
|---|---|
| author | Roth, Amit Turetzky, Arnon Adi, Yossi |
| author_facet | Roth, Amit Turetzky, Arnon Adi, Yossi |
| contents | We tackle the task of text-to-speech (TTS) in Hebrew. Traditional Hebrew contains Diacritics, which dictate the way individuals should pronounce given words, however, modern Hebrew rarely uses them. The lack of diacritics in modern Hebrew results in readers expected to conclude the correct pronunciation and understand which phonemes to use based on the context. This imposes a fundamental challenge on TTS systems to accurately map between text-to-speech. In this work, we propose to adopt a language modeling Diacritics-Free approach, for the task of Hebrew TTS. The model operates on discrete speech representations and is conditioned on a word-piece tokenizer. We optimize the proposed method using in-the-wild weakly supervised data and compare it to several diacritic-based TTS systems. Results suggest the proposed method is superior to the evaluated baselines considering both content preservation and naturalness of the generated speech. Samples can be found under the following link: pages.cs.huji.ac.il/adiyoss-lab/HebTTS/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12206 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Language Modeling Approach to Diacritic-Free Hebrew TTS Roth, Amit Turetzky, Arnon Adi, Yossi Computation and Language Sound Audio and Speech Processing We tackle the task of text-to-speech (TTS) in Hebrew. Traditional Hebrew contains Diacritics, which dictate the way individuals should pronounce given words, however, modern Hebrew rarely uses them. The lack of diacritics in modern Hebrew results in readers expected to conclude the correct pronunciation and understand which phonemes to use based on the context. This imposes a fundamental challenge on TTS systems to accurately map between text-to-speech. In this work, we propose to adopt a language modeling Diacritics-Free approach, for the task of Hebrew TTS. The model operates on discrete speech representations and is conditioned on a word-piece tokenizer. We optimize the proposed method using in-the-wild weakly supervised data and compare it to several diacritic-based TTS systems. Results suggest the proposed method is superior to the evaluated baselines considering both content preservation and naturalness of the generated speech. Samples can be found under the following link: pages.cs.huji.ac.il/adiyoss-lab/HebTTS/ |
| title | A Language Modeling Approach to Diacritic-Free Hebrew TTS |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.12206 |