Recently, Transformer-based architectures have been explored for speaker...
Recent research showed that the dual-pixel sensor has made great progres...
In this report, we describe our submitted system for track 2 of the VoxC...
In order to improve the vessel's capacity and ensure maritime traffic sa...
There are numerous types of programming languages developed in the last
...
In this paper, a family of novel diffusion adaptive estimation algorithm...
This paper describes the Microsoft speaker diarization system for monaur...
Reverse-engineering bar charts extracts textual and numeric information ...
ResNet-based architecture has been widely adopted as the speaker embeddi...
Materials representation plays a key role in machine learning based
pred...
Machine learning (ML) methods have gained increasing popularity in explo...
John Desmond Bernal (1901-1970) was one of the most eminent scientists i...
Noncentrosymmetric materials play a critical role in many important
appl...
This paper describes a system that generates speaker-annotated transcrip...
A major challenge in materials design is how to efficiently search the v...
Modern deep neural network models generally build upon heavy
over-parame...
Typical methods for supervised sequence modeling are built upon the recu...
Deep neural networks have shown excellent performance in stereo matching...
The use of deep networks to extract embeddings for speaker recognition h...
The teacher-student (T/S) learning has been shown to be effective for a
...
SLAM technology has recently seen many successes and attracted the atten...
State-of-the-art face recognition algorithms are able to achieve good
pe...
We propose two approaches for speaker adaptation in end-to-end (E2E)
aut...
We propose a novel adversarial multi-task learning scheme, aiming at act...
Convolutional neural networks(CNN) have been shown to perform better tha...
Single Shot MultiBox Detector (SSD) is one of the fastest algorithms in ...
The split control and user plane is key to the future heterogeneous cell...
Visual tracking is intrinsically a temporal problem. Discriminative
Corr...
A new type of End-to-End system for text-dependent speaker verification ...
The omnipresence of deep learning architectures such as deep convolution...
We trained Binarized Neural Networks (BNNs) on the high resolution Image...