Publications

カンファレンス (国際) SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark

Yuki Saito (The University of Tokyo), Takuto Igarashi (The University of Tokyo), Kentaro Seki (The University of Tokyo), Shinnosuke Takamichi (The University of Tokyo), Ryuichi Yamamoto, Kentaro Tachibana, Hiroshi Saruwatari (The University of Tokyo)

The 25th Annual Conference of the International Speech Communication Association (INTERSPEECH 2024)

2024.9.1

We present SRC4VC, a new corpus containing 11 hours of speech recorded on smartphones by 100 Japanese speakers. Although high-quality multi-speaker corpora can advance voice conversion (VC) technologies, they are not always suitable for testing VC when low-quality speech recording is given as the input. To this end, we first asked 100 crowdworkers to record their voice samples using smartphones. Then, we annotated the recorded samples with speaker-wise recording-quality scores and utterance-wise perceived emotion labels. We also benchmark SRC4VC on any-to-any VC, in which we trained a multi-speaker VC model on high-quality speech and used the SRC4VC speakers’ voice samples as the source in VC. The results show that the recording quality mismatch between the training and evaluation data significantly degrades the VC performance, which can be improved by applying speech enhancement to the low-quality source speech samples.

Paper : SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark新しいタブまたはウィンドウで開く (外部サイト)

PDF : SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark