Yossi Adi
Yossi Adi wrote 3 of the papers Mova reads, in 2024; often with Amit Roth, Arnon Turetzky, Ella Zeldes.
Papers
- A Language Modeling Approach to Diacritic-Free Hebrew TTS (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… - Enhancing TTS Stability in Hebrew using Discrete Semantic Units (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… - HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing (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 ×2
- Arnon Turetzky ×2
- Ella Zeldes ×2
- Or Tal ×2
- Bronya R. Chernyak
- Eyal Cohen
- Joseph Keshet
- Olga Seleznova
- Yael Segal-Feldman
- Yehoshua Dissen
- Yosi Shrem
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/yossi-adi/