Showing 1–11 of 11 results
/ Date/ Name
Oct 10, 2018Fully Supervised Speaker DiarizationApr 14, 2014Recover Canonical-View Faces in the Wild with Deep Neural NetworksMar 31, 2016Learning Multiscale Features Directly From WaveformsMar 1, 2017Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence LabellingJun 26, 2014Deep Learning Multi-View Representation for Face RecognitionMay 5, 2017Deep Speaker: an End-to-End Neural Speaker Embedding SystemMay 11, 2017Reducing Bias in Production Speech ModelsJul 24, 2017Exploring Neural Transducers for End-to-End Speech RecognitionDec 8, 2015Deep Speech 2: End-to-End Speech Recognition in English and MandarinSep 11, 2014DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detectionMay 25, 2017Principled Hybrids of Generative and Discriminative Domain Adaptation