Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models

In this paper we investigate the GMM-derived (GMMD) features for adaptation of deep neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD features is done through the maximum a posteriori (MAP) adaptation of the auxiliary GMM model used for GMMD feature extraction. We explo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-03
Hauptverfasser:	Tomashenko, Natalia, Khokhlov, Yuri, Esteve, Yannick
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Artificial neural networks Error reduction Feature extraction Level (quantity) Mathematical analysis Neural networks Probabilistic models Regression analysis Vectors (mathematics)
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!