Speech Separation On Whamr
المقاييس
SI-SDRi
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | SI-SDRi |
|---|---|
| separate-and-reconstruct-asymmetric-encoder | 17.1 |
| wham-extending-speech-separation-to-noisy | 9.2 |
| stepwise-refining-speech-separation-network | 12.3 |
| on-time-domain-conformer-models-for-monaural | 10.5 |
| mossformer-pushing-the-performance-limit-of | 16.3 |
| on-time-domain-conformer-models-for-monaural | 13.4 |
| voice-separation-with-an-unknown-number-of | 12.2 |
| stepwise-refining-speech-separation-network | 12.3 |
| tf-locoformer-transformer-with-local-modeling | 18.5 |
| deformable-temporal-convolutional-networks | 11.1 |
| on-time-domain-conformer-models-for-monaural | 14.6 |
| wavesplit-end-to-end-speech-separation-by | 13.2 |
| compute-and-memory-efficient-universal-sound | 13.5 |
| deformable-temporal-convolutional-networks | 10.1 |
| mossformer2-combining-transformer-and-rnn-1 | 17.0 |
| sudo-rm-rf-efficient-networks-for-universal | 12.1 |
| tf-locoformer-transformer-with-local-modeling | 17.4 |
| on-time-domain-conformer-models-for-monaural | 12 |