Phonikud: Hebrew Grapheme-to-Phoneme Conversion for Real-Time Text-to-Speech

TL;DR

Phonikud is a new lightweight Hebrew G2P system that produces fully-specified IPA transcriptions, improving real-time TTS accuracy and speed, supported by a new benchmark dataset.

Contribution

We introduce Phonikud, a novel Hebrew G2P system with minimal latency, and the ILSpeech dataset for benchmarking Hebrew phonetic conversion and TTS evaluation.

Findings

Phonikud outperforms prior G2P methods in accuracy.

Enables effective real-time Hebrew TTS with better speed-accuracy balance.

Provides a new benchmark dataset for Hebrew speech and phonetic research.

Abstract

Real-time text-to-speech (TTS) for Modern Hebrew is challenging due to the language's orthographic complexity. Existing solutions ignore crucial phonetic features such as stress that remain underspecified even when vowel marks are added. To address these limitations, we introduce Phonikud, a lightweight, open-source Hebrew grapheme-to-phoneme (G2P) system that outputs fully-specified IPA transcriptions. Our approach adapts an existing diacritization model with lightweight adaptors, incurring negligible additional latency. We also contribute the ILSpeech dataset of transcribed Hebrew speech with IPA annotations, serving as a benchmark for Hebrew G2P, as training data for TTS systems, and enabling audio-to-IPA for evaluating TTS performance while capturing important phonetic details. Our results demonstrate that Phonikud G2P conversion more accurately predicts phonemes from Hebrew text compared to prior methods, and that this enables training of effective real-time Hebrew TTS models with superior speed-accuracy trade-offs. We release our code, data, and models at https: //phonikud.github.io.