Papers by Vijval Ekbote
IndicSynth: A Large-Scale Multilingual Synthetic Speech Dataset for Low-Resource Indian Languages (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in synthetic speech generation technology have enabled the generation of high-quality synthetic (fake) speech that emulates human voices. |
| Approach: | They propose a dataset that contains 4,000 hours of synthetic speech from 989 target speakers for 12 low-resourced Indian languages. |
| Outcome: | The proposed dataset contains 4,000 hours of synthetic speech from 989 target speakers, including 456 females and 533 males for 12 low-resourced Indian languages. |