---
title: "Ella Zeldes — papers and cards"
description: "Ella Zeldes: 2 paper cards in the Research library (2024), with what each paper is about, the ideas Mova took from it, and the co-authors."
canonical: "https://research.elamur.ai/free/en/authors/ella-zeldes/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/ella-zeldes/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Ella Zeldes

# Ella Zeldes

2 paper cards in the Research library · 2024

Ella Zeldes wrote 2 of the papers Mova reads, in 2024; often with [Or Tal](https://md.research.elamur.ai/free/en/authors/or-tal/), [Yossi Adi](https://md.research.elamur.ai/free/en/authors/yossi-adi/), [Amit Roth](https://md.research.elamur.ai/free/en/authors/amit-roth/).

[OpenAlex](https://openalex.org/A5104431190) · [**h-index 1**](https://openalex.org/authors/A5104431190) · [2 citations](https://openalex.org/authors/A5104431190) · [2 works](https://openalex.org/works?filter=author.id:A5104431190) — openalex-snapshot, 2026-10-14

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

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

## Papers

1. **[HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing](https://md.research.elamur.ai/free/en/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.
2. **[Enhancing TTS Stability in Hebrew using Discrete Semantic Units](https://md.research.elamur.ai/free/en/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…

## Co-authors (11)

- [Or Tal](https://md.research.elamur.ai/free/en/authors/or-tal/) ×2
- [Yossi Adi](https://md.research.elamur.ai/free/en/authors/yossi-adi/) ×2
- [Amit Roth](https://md.research.elamur.ai/free/en/authors/amit-roth/)
- [Arnon Turetzky](https://md.research.elamur.ai/free/en/authors/arnon-turetzky/)
- Bronya R. Chernyak
- Eyal Cohen
- Joseph Keshet
- Olga Seleznova
- Yael Segal-Feldman
- Yehoshua Dissen
- Yosi Shrem