Papers with NIST 2021 Speaker Recognition Evaluation
WeCanTalk: A New Multi-language, Multi-modal Resource for Speaker Recognition (2022.lrec-1)
Copied to clipboard
| Challenge: | The WeCanTalk corpus is a multi-modal, multi-language resource for speaker recognition. |
| Approach: | The WeCanTalk corpus is a multi-modal resource for speaker recognition. |
| Outcome: | The corpus contains data from 202 native speakers in Hong Kong who were fluent in at least one other language. |