SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916283103051776 |
|---|---|
| author | Saito, Yuki Igarashi, Takuto Seki, Kentaro Takamichi, Shinnosuke Yamamoto, Ryuichi Tachibana, Kentaro Saruwatari, Hiroshi |
| author_facet | Saito, Yuki Igarashi, Takuto Seki, Kentaro Takamichi, Shinnosuke Yamamoto, Ryuichi Tachibana, Kentaro Saruwatari, Hiroshi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07254 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark Saito, Yuki Igarashi, Takuto Seki, Kentaro Takamichi, Shinnosuke Yamamoto, Ryuichi Tachibana, Kentaro Saruwatari, Hiroshi Sound Audio and Speech Processing 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. |
| title | SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.07254 |