POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
School of Computer Science, Carnegie Mellon University · UC Berkeley, University of California, Berkeley · University of Texas at Austin · University of British Columbia · Japan Broadcasting Corporation, Tohoku University and Carnegie Mellon University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。DOI 10.18653/v1/2026.acl-long.813 ↗
摘要
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, models, and code are released to foster open science.