A convolutional neural network (CNN) is one of the most significant networks in the deep
learning field. Since CNN made impressive achievements in many areas, including but not …

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto
standard for various Computer Vision and Machine Learning operations. CNNs are feed …

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized
computer vision through end‐to‐end learning, that is, learning from the raw data. There is …

We describe the latest version of Microsoft's conversational speech recognition system for
the Switchboard and CallHome domains. The system adds a CNN-BLSTM acoustic model to …

Current RGB-D salient object detection (SOD) methods utilize the depth stream as
complementary information to the RGB stream. However, the depth maps are usually of low …

Software frameworks for neural networks play key roles in the development and application
of deep learning methods. However, as new types of deep learning models are developed …

Conversational speech recognition has served as a flagship speech recognition task since
the release of the Switchboard corpus in the 1990s. In this paper, we measure the human …

Sequence-to-sequence models have shown success in end-to-end speech recognition.
However these models have only used shallow acoustic encoder networks. In our work, we …

Layer-sequential unit-variance (LSUV) initialization-a simple method for weight initialization
for deep net learning-is proposed. The method consists of the two steps. First, pre-initialize …

Learning acoustic models directly from the raw waveform data with minimal processing is
challenging. Current waveform-based models have generally used very few (~ 2) …