Lanean...

Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training

Although deep neural network (DNN) acoustic models are known to be inherently noise robust, especially with matched training and testing data, the use of speech separation as a frontend and for deriving alternative feature representations has been shown to improve performance in challenging environm...

Deskribapen osoa

Gorde:
Xehetasun bibliografikoak
Argitaratua izan da:IEEE/ACM Trans Audio Speech Lang Process
Egile Nagusiak: Narayanan, Arun, Wang, DeLiang
Formatua: Artigo
Hizkuntza:Inglês
Argitaratua: 2015
Gaiak:
Sarrera elektronikoa:https://ncbi.nlm.nih.gov/pmc/articles/PMC4784988/
https://ncbi.nlm.nih.gov/pubmed/26973851
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1109/TASLP.2014.2372314
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!