Lanean...
Estimating nonnegative matrix model activations with deep neural networks to increase perceptual speech quality
As a means of speech separation, time-frequency masking applies a gain function to the time-frequency representation of noisy speech. On the other hand, nonnegative matrix factorization (NMF) addresses separation by linearly combining basis vectors from speech and noise models to approximate noisy s...
Gorde:
| Argitaratua izan da: | J Acoust Soc Am |
|---|---|
| Egile Nagusiak: | , , |
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
Acoustical Society of America
2015
|
| Gaiak: | |
| Sarrera elektronikoa: | https://ncbi.nlm.nih.gov/pmc/articles/PMC5392055/ https://ncbi.nlm.nih.gov/pubmed/26428778 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1121/1.4928612 |
| Etiketak: |
Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|