Speaker adaptation of deep neural network acoustic models using Gaussian mixture model framework in automatic speech recognition systems
N Tomashenko - 2017 - theses.hal.science
Differences between training and testing conditions may significantly degrade recognition
accuracy in automatic speech recognition (ASR) systems. Adaptation is an efficient way to …
accuracy in automatic speech recognition (ASR) systems. Adaptation is an efficient way to …
Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models
N Tomashenko, Y Khokhlov, Y Estève - arXiv preprint arXiv:2003.06894, 2020 - arxiv.org
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 …
neural network (DNN) acoustic models. The adaptation of the DNN trained on GMMD …