mlsanityData to 14 Oct 2026

Phonikud: Overcoming Phonetic Underspecification for Hebrew Text-To-Speech

arXiv 2506.12311 ↗First posted 14 Jun 2025cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-speech (TTS) for Modern Hebrew is challenged by the language's orthographic complexity, with existing solutions ignoring underspecified phonetic features such as stress. We present a framework for more phonetically accurate Hebrew TTS with four contributions: (1) Phonikud, an open-source Hebrew grapheme-to-phoneme (G2P) system that outputs fully-specified International Phonetic Alphabet (IPA) transcriptions, designed by augmenting a base diacritizer. (2) The ILSpeech corpus of paired Hebrew audio, text, and expert IPA annotations. (3) A benchmark for the previously unmeasured task of Hebrew G2P conversion. (4) Hebrew audio-to-IPA models capturing previously disregarded phonetic details for automatic TTS evaluation. Our results show that Phonikud more accurately predicts Hebrew phonemes than prior methods, and that small, local TTS models with phonetic input from Phonikud approach large proprietary systems. We release our code, data, and models at https://phonikud.github.io.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 27 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

10 of 27 references.

References · 10

  1. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  2. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  3. 2023Scaling Speech Technology to 1,000+ Languagescited by 411
  4. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
  5. 2022ByT5 model for massively multilingual grapheme-to-phoneme conversioncited by 49
  6. 2023DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrewcited by 17
  7. 2021Restoring Hebrew Diacritics Without a Dictionarycited by 10
  8. 2024HebDB: a Weakly Supervised Dataset for Hebrew Speech Processingcited by 3
  9. 2024A Language Modeling Approach to Diacritic-Free Hebrew TTScited by 2
  10. 2024Enhancing TTS Stability in Hebrew using Discrete Semantic Unitscited by 2

Built on by

Not cited yet.