[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/yossi-adi/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Yossi Adi

# Yossi Adi

3 paper cards in Mova's library · 2024

Yossi Adi wrote 3 of the papers Mova reads, in 2024; often with [Amit Roth](https://md.mova.elamur.ai/free/en/docs/papers/authors/amit-roth/), [Arnon Turetzky](https://md.mova.elamur.ai/free/en/docs/papers/authors/arnon-turetzky/), [Ella Zeldes](https://md.mova.elamur.ai/free/en/docs/papers/authors/ella-zeldes/).

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Yossi+Adi) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yossi+Adi) · [dblp](https://dblp.org/search?q=Yossi+Adi) · [ACL Anthology](https://aclanthology.org/search/?q=Yossi+Adi) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Yossi+Adi)

## Papers

1. **[A Language Modeling Approach to Diacritic-Free Hebrew TTS](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-roth-language-modeling-approach-diacritic-free/)** *(2024)* The authors build a text-to-speech system for undotted (undiacritized) Hebrew. An autoregressive language model over discrete EnCodec tokens is conditioned on a word-piece encoding of the plain text, with a 3-second acoustic prompt. The model is trained on about 4,500 hours of weakly transcribed podcast speech…
2. **[Enhancing TTS Stability in Hebrew using Discrete Semantic Units](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-zeldes-enhancing-tts-stability-hebrew-using/)** *(2024)* The paper presents LoTHM, a text-to-speech language model for unvocalised Hebrew. It predicts HuBERT semantic units rather than acoustic codec tokens, so no separate diacritisation step is needed; a vocoder with a speaker embedding then turns the units into audio. The training data is about 4,500 hours of Hebrew…
3. **[HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-turetzky-hebdb-weakly-supervised-dataset-hebrew/)** *(2024)* HebDB is a speech corpus of roughly 2,500 hours of spontaneous Hebrew: podcasts on many topics plus testimonies of World War II survivors, released both raw and pre-processed.

## Co-authors (11)

- [Amit Roth](https://md.mova.elamur.ai/free/en/docs/papers/authors/amit-roth/) ×2
- [Arnon Turetzky](https://md.mova.elamur.ai/free/en/docs/papers/authors/arnon-turetzky/) ×2
- [Ella Zeldes](https://md.mova.elamur.ai/free/en/docs/papers/authors/ella-zeldes/) ×2
- [Or Tal](https://md.mova.elamur.ai/free/en/docs/papers/authors/or-tal/) ×2
- Bronya R. Chernyak
- Eyal Cohen
- Joseph Keshet
- Olga Seleznova
- Yael Segal-Feldman
- Yehoshua Dissen
- Yosi Shrem
- [← previous Yonatan Belinkov](https://md.mova.elamur.ai/free/en/docs/papers/authors/yonatan-belinkov/)
- [next → Younes Samih](https://md.mova.elamur.ai/free/en/docs/papers/authors/younes-samih/)
- [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)