GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929393793761280 |
|---|---|
| author | Wang, Wenbin Song, Yang Jha, Sanjay |
| author_facet | Wang, Wenbin Song, Yang Jha, Sanjay |
| contents | This paper introduces GLOBE, a high-quality English corpus with worldwide accents, specifically designed to address the limitations of current zero-shot speaker adaptive Text-to-Speech (TTS) systems that exhibit poor generalizability in adapting to speakers with accents. Compared to commonly used English corpora, such as LibriTTS and VCTK, GLOBE is unique in its inclusion of utterances from 23,519 speakers and covers 164 accents worldwide, along with detailed metadata for these speakers. Compared to its original corpus, i.e., Common Voice, GLOBE significantly improves the quality of the speech data through rigorous filtering and enhancement processes, while also populating all missing speaker metadata. The final curated GLOBE corpus includes 535 hours of speech data at a 24 kHz sampling rate. Our benchmark results indicate that the speaker adaptive TTS model trained on the GLOBE corpus can synthesize speech with better speaker similarity and comparable naturalness than that trained on other popular corpora. We will release GLOBE publicly after acceptance. The GLOBE dataset is available at https://globecorpus.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14875 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech Wang, Wenbin Song, Yang Jha, Sanjay Sound Audio and Speech Processing This paper introduces GLOBE, a high-quality English corpus with worldwide accents, specifically designed to address the limitations of current zero-shot speaker adaptive Text-to-Speech (TTS) systems that exhibit poor generalizability in adapting to speakers with accents. Compared to commonly used English corpora, such as LibriTTS and VCTK, GLOBE is unique in its inclusion of utterances from 23,519 speakers and covers 164 accents worldwide, along with detailed metadata for these speakers. Compared to its original corpus, i.e., Common Voice, GLOBE significantly improves the quality of the speech data through rigorous filtering and enhancement processes, while also populating all missing speaker metadata. The final curated GLOBE corpus includes 535 hours of speech data at a 24 kHz sampling rate. Our benchmark results indicate that the speaker adaptive TTS model trained on the GLOBE corpus can synthesize speech with better speaker similarity and comparable naturalness than that trained on other popular corpora. We will release GLOBE publicly after acceptance. The GLOBE dataset is available at https://globecorpus.github.io/. |
| title | GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.14875 |