Yossi Adi

3 paper cards in the Research library · 2024

Yossi Adi wrote 3 of the papers Mova reads, in 2024; often with Amit Roth, Arnon Turetzky, Ella Zeldes.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

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.
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…

Pages of the Research library: our summary, the ideas, references and who cites each.