Discriminative frequency filter banks learning with neural networks
Abstract Filter banks on spectrums play an important role in many audio applications. Traditionally, the filters are linearly distributed on perceptual frequency scale such as Mel scale. To make the output smoother, these filters are often placed so that they overlap with each other. However, fixed-...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Artigo |
| Lenguaje: | Inglês |
| Publicado: |
SpringerOpen
2019-01-01
|
| Colección: | EURASIP Journal on Audio, Speech, and Music Processing |
| Materias: | |
| Acceso en línea: | http://link.springer.com/article/10.1186/s13636-018-0144-6 |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|