Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations

About

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/

Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Yu Zhang, Wei Han, Ankur Bapna, Michiel Bacchiani• 2023

Related benchmarks

TaskDatasetResultRank
General Speech RestorationDNS-Real Out-Domain (test)
SIG3.325
9
General Speech RestorationVoicefixer-GSR In-Domain (test)
SIG3.335
7
General Speech RestorationDNS-with-Reverb Out-Domain (test)
SIG3.401
7
Showing 3 of 3 rows

Other info

Follow for update