Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations
Koizumi, Yuma, Zen, Heiga, Karita, Shigeki, Ding, Yifan, Yatabe, Kohei, Morioka, Nobuyuki, Zhang, Yu, Han, Wei, Bapna, Ankur, Bacchiani, Michiel
–arXiv.org Artificial Intelligence
Speech restoration (SR) is a task of converting degraded speech signals into high-quality ones. In this study, we propose a robust SR model called Miipher, and apply Miipher to a new SR application: increasing the amount of high-quality training data for speech generation by converting speech samples collected from the Web to studio-quality. To make our SR model robust against various degradation, we use (i) a speech representation extracted from w2v-BERT for the input feature, and (ii) a text representation extracted from transcripts via PnG-BERT as a linguistic conditioning feature. Experiments show that Miipher (i) is robust against various audio degradation and (ii) enable us to train a high-quality text-to-speech (TTS) model from restored speech samples collected from the Web. Audio samples are available at our demo page: google.github.io/df-conformer/miipher/
arXiv.org Artificial Intelligence
Aug-14-2023
- Genre:
- Research Report > New Finding (0.35)
- Industry:
- Media (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (0.93)
- Speech (1.00)
- Information Technology > Artificial Intelligence