Research Article
Anime Audio Retrieval Based on Audio Separation and Feature Recognition
Table 1
The detail information of the model.
| | Parameters | Values |
| | Number of downsampling blocks in encoder | 5 | | Number of upsampling blocks in decoder | 5 | | Kernel size | 3 | | Stride of audio separation model | 1 | | Stride of audio fingerprinting model | 2 | | Number of convolutional layers in audio fingerprinting model | 8 |
|
|
