Pretraining

TCS Research at SemEval-2018 Task 1: Learning Robust Representations using Multi-Attention Architecture SemEval 2018 Adversarial Network Bottleneck Features for Noise Robust Speaker Verification Interspeech 2017 An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation Interspeech 2017 A Transfer Learning Based Feature Extractor for Polyphonic Sound Event Detection Using Connectionist Temporal Classification Interspeech 2017 CNN-SLAM: Real-Time Dense Monocular SLAM With Learned Depth Prediction CVPR 2017 Colorization as a Proxy Task for Visual Understanding CVPR 2017 Deep Feature Interpolation for Image Content Changes CVPR 2017 Deep Network Flow for Multi-Object Tracking CVPR 2017 Deep Speaker Feature Learning for Text-Independent Speaker Verification Interspeech 2017 Deep Tensor Convolution on Multicores ICML 2017 Embedding-Based Speaker Adaptive Training of Deep Neural Networks Interspeech 2017 End-to-End Deep Learning Framework for Speech Paralinguistics Detection Based on Perception Aware Spectrum Interspeech 2017 End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow Interspeech 2017 Exploring Personalized Neural Conversational Models IJCAI 2017 Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings EACL 2017 Image-to-Markup Generation with Coarse-to-Fine Attention ICML 2017 Improving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer Interspeech 2017 Inference Compilation and Universal Probabilistic Programming AISTATS 2017 Learning From Synthetic Humans CVPR 2017 Limits of End-to-End Learning ACML 2017 Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search CVPR 2017 Neural Word Segmentation with Rich Pretraining ACL 2017 Stacked Generative Adversarial Networks CVPR 2017 The INTERSPEECH 2017 Computational Paralinguistics Challenge: Addressee, Cold & Snoring Interspeech 2017 Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition Interspeech 2017