# ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion

arXiv: https://arxiv.org/abs/2606.20179 · HTML: https://mlsanity.com/paper/2606.20179/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [ByT5 model for massively multilingual grapheme-to-phoneme conversion](https://mlsanity.com/paper/2204.03067/) (2022)
- [DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew](https://mlsanity.com/paper/2308.16687/) (2023)
- [POWSM: A Phonetic Open Whisper-Style Speech Foundation Model](https://mlsanity.com/paper/2510.24992/) (2025)
- [Restoring Hebrew Diacritics Without a Dictionary](https://mlsanity.com/paper/2105.05209/) (2021)
- [Automatic Restoration of Diacritics for Speech Data Sets](https://mlsanity.com/paper/2311.10771/) (2023)
- [Improving grapheme-to-phoneme conversion by learning pronunciations from speech recordings](https://mlsanity.com/paper/2307.16643/) (2023)
- [Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning](https://mlsanity.com/paper/2409.09891/) (2024)
- [VoxKnesset: A Large-Scale Longitudinal Hebrew Speech Dataset for Aging Speaker Modeling](https://mlsanity.com/paper/2603.01270/) (2026)

## Built on by (most cited first, 1 of 1)

- [SHAMS: An Audio-Grounded Pronunciation Benchmark for Levantine Arabic](https://mlsanity.com/paper/2610.01427/) (2026)

## Abstract (arXiv)

Grapheme-to-phoneme (G2P) conversion for Modern Hebrew is needed for applications like text-to-speech (TTS), but is challenging due to the language's abjad writing system, which leaves vowels largely unwritten, creating substantial ambiguity. Standard approaches first predict vowel diacritics (nikud) to produce International Phonetic Alphabet (IPA) transcriptions, but this is limited: vocalization data is scarce and laborious to produce, it does not specify features such as lexical stress, and it reflects formal grammatical rules rather than everyday spoken pronunciation. Direct sequence-to-sequence IPA prediction, meanwhile, struggles on limited data and fails to exploit the character-level alignment characteristic of abjads. Our method, ReNikud, overcomes these limitations with two key insights: (1) Weak audio supervision via a phoneme-based automatic speech recognition (ASR) pseudo-labeling pipeline on thousands of hours of unlabeled Hebrew audio, yielding phonemic transcriptions that reflect natural spoken norms without manual annotation. (2) A pseudo-vocalization architecture that predicts IPA phonemes at each character position, enforcing character-level alignment as an inductive bias. Results on existing Hebrew G2P benchmarks and the new targeted MILIM benchmark for spoken Hebrew show that ReNikud surpasses previous state-of-the-art methods. We will release our code and trained models to support further work on Hebrew TTS and speech technologies.