M
Maofan Yin
Researcher at Shanghai Jiao Tong University
Publications - Â 4
Citations - Â 120
Maofan Yin is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Speaker recognition & Artificial neural network. The author has an hindex of 4, co-authored 4 publications receiving 110 citations.
Papers
More filters
Proceedings ArticleDOI
Cluster adaptive training for deep neural network
TL;DR: The cluster adaptive training (CAT) framework for DNN adaptation is employed, here, multiple DNNs are constructed to form the bases of a canonical parametric space and an interpolation vector, specific to a particular acoustic condition, is used to combine themultiple DNN bases into a single adapted DNN.
Proceedings ArticleDOI
Multi-task joint-learning of deep neural networks for robust speech recognition
TL;DR: A novel multi-task joint-learning framework is proposed to address the noise robustness for speech recognition and can achieve a WER below 10% without using adaptation or sequence training, a very large and significant improvement over a strong DNN-HMM baseline.
Proceedings ArticleDOI
Multi-task joint-learning for robust voice activity detection
TL;DR: A new structured multi-frame prediction DNN approach is proposed to improve the segment-level VAD performance and is shown to be much more robust than conventional DNN based VAD.
Proceedings ArticleDOI
Discriminatively trained joint speaker and environment representations for adaptation of deep neural network acoustic models
TL;DR: This paper proposes a novel approach for estimating a compact joint representation of speakers and environment by training a DNN, with a bottleneck layer, to classify the i-vector features into speaker and environment labels by Multi-Task Learning (MTL).