This paper ports the idea of. SAT to deep neural networks (DNNs), and proposes a framework to perform feature-space SAT for DNNs. Using i-vectors as speaker ...
Abstract: We propose to adapt deep neural network (DNN) acoustic models to a target speaker by supplying speaker identity vectors (i-vectors) as input ...
Missing: Adaptive | Show results with:Adaptive
Jul 16, 2015 · This paper ports the idea of SAT to deep neural networks (DNNs), and proposes a framework to perform feature-space SAT for DNNs. Using i-vectors ...
This paper ports the idea of SAT to deep neural networks (DNNs), and proposes a framework to perform feature-space SAT for DNNs, using i-vectors as speaker ...
Abstract—We propose to adapt deep neural network (DNN) acoustic models to a target speaker by supplying speaker identity vectors (i-vectors) as input ...
Oct 17, 2017 · An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling ...
Training of SAT-DNN models starts from fully-trained DNN models. We then train a smaller neural network iVecNN which takes speaker i-vectors as inputs and ...
In this paper, we apply SAT to DNNs by learning two types of feature mapping neural networks. Given an initial DNN model, these networks take speaker i-vectors ...
This work proposes to adapt deep neural network acoustic models to a target speaker by supplying speaker identity vectors (i-vectors) as input features to ...
May 22, 2018 · Title of thesis : Speaker adaptation of deep neural network acoustic models using Gaussian mixture model framework in automatic speech ...