POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915735138205696 |
|---|---|
| author | Li, Chin-Jou Chang, Kalvin Bharadwaj, Shikhar Yeo, Eunjung Choi, Kwanghee Zhu, Jian Mortensen, David Watanabe, Shinji |
| author_facet | Li, Chin-Jou Chang, Kalvin Bharadwaj, Shikhar Yeo, Eunjung Choi, Kwanghee Zhu, Jian Mortensen, David Watanabe, Shinji |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24992 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | POWSM: A Phonetic Open Whisper-Style Speech Foundation Model Li, Chin-Jou Chang, Kalvin Bharadwaj, Shikhar Yeo, Eunjung Choi, Kwanghee Zhu, Jian Mortensen, David Watanabe, Shinji Computation and Language Audio and Speech Processing 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. |
| title | POWSM: A Phonetic Open Whisper-Style Speech Foundation Model |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.24992 |