Caricamento...

Fast speaker adaptation using extended diagonal linear transformation for deep neural networks

This paper explores new techniques that are based on a hidden‐layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwh...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Autori principali: Donghyun Kim, Sanghun Kim
Natura: Artigo
Lingua:Inglês
Pubblicazione: Electronics and Telecommunications Research Institute (ETRI) 2018-11-01
Serie:ETRI Journal
Soggetti:
Accesso online:https://doi.org/10.4218/etrij.2017-0087
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne! !