On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification

Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extracting bottleneck (BN) features, the key considerations include training targets, activation functions, and loss functions....

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Achintya Kumar Sarkar, Zheng-Hua Tan
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2023-07-01
Schriftenreihe:	Acoustics
Schlagworte:	training targets activation functions loss functions bottleneck features text-dependent speaker verification
Online-Zugang:	https://www.mdpi.com/2624-599X/5/3/42
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!