Robust Audio-visual Speech Recognition Using Bimodal Dfsmn with Multi-condition Training and Dropout Regularization

Shiliang Zhang(Alibaba Group (United States)), Lei Xie(Northwestern Polytechnical University), Ming Lei(Beijing University of Posts and Telecommunications), Bin Ma(Alibaba Group (United States))
Unknown
April 17, 2019
10.1109/icassp.2019.8682566
Cited by 38

Related Papers

Machine learning in materials science
|InfoMat|2019|999
The Cancer Microbiome: Distinguishing Direct and Indirect Effects Requires a Systemic View
|Trends in cancer|2020|266
Deep-FSMN for Large Vocabulary Continuous Speech Recognition
|Unknown|2018|128
Crowdsourced mapping of unexplored target space of kinase inhibitors
|Nature Communications|2021|88
A Steel Surface Defect Recognition Algorithm Based on Improved Deep Learning Network Model Using Feature Visualization and Quality Evaluation
|IEEE Access|2020|76