Text-to-Audio Retrieval on Speech (test)
7.1R@1Speech-CLAP
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Speech-CLAPbackbone=WavLM2023.12 | 7.1 | 16.3 | 22.01 | |
| CLAPvariant=with speech2023.12 | 0.82 | 2.42 | 3.37 | |
| CLAPvariant=general audio2023.12 | 0.36 | 1.29 | 2.29 |
| Method | Links | |||
|---|---|---|---|---|
| Speech-CLAPbackbone=WavLM2023.12 | 7.1 | 16.3 | 22.01 | |
| CLAPvariant=with speech2023.12 | 0.82 | 2.42 | 3.37 | |
| CLAPvariant=general audio2023.12 | 0.36 | 1.29 | 2.29 |