Combines learned time-frequency representation with a masker architecture based on 1D dilated convolution.
Source: Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech SeparationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Separation | 8 | 42.11% |
Speech Enhancement | 3 | 15.79% |
Action Detection | 1 | 5.26% |
Activity Detection | 1 | 5.26% |
Speaker Diarization | 1 | 5.26% |
Denoising | 1 | 5.26% |
Audio Source Separation | 1 | 5.26% |
Speaker Recognition | 1 | 5.26% |
Music Source Separation | 1 | 5.26% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |