POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
This work addresses the need for integrated phonetic processing, potentially benefiting universal and low-resource speech applications, though it is incremental as it builds on existing whisper-style models.
The paper tackles the problem of isolated phonetic tasks in spoken language processing by introducing POWSM, a unified framework that jointly performs multiple phone-related tasks, achieving performance that matches or outperforms specialized models of similar size.
Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion (P2G). Despite their conceptual similarity, these tasks have largely been studied in isolation, each relying on task-specific architectures and datasets. In this paper, we introduce POWSM (Phonetic Open Whisper-style Speech Model), the first unified framework capable of jointly performing multiple phone-related tasks. POWSM enables seamless conversion between audio, text (graphemes), and phones, opening up new possibilities for universal and low-resource speech processing. Our model outperforms or matches specialized PR models of similar size (Wav2Vec2Phoneme and ZIPA) while jointly supporting G2P, P2G, and ASR. Our training data, code and models are released to foster open science.