Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Visual speech recognition (VSR) aims to recognize the content of speech based on lip
movements, without relying on the audio stream. Advances in deep learning and the …

We present SpecAugment, a simple data augmentation method for speech recognition.
SpecAugment is applied directly to the feature inputs of a neural network (ie, filter bank …

Multi-object tracking (MOT) aims to associate target objects across video frames in order to
obtain entire moving trajectories. With the advancement of deep neural networks and the …

We present a simple and efficient auxiliary loss function for automatic speech recognition
(ASR) based on the connectionist temporal classification (CTC) objective. The proposed …

Sequence-to-sequence attention-based models on subword units allow simple open-
vocabulary end-to-end speech recognition. In this work, we show that such models can …

Exploring spatial-temporal dependencies from observed motions is one of the core
challenges of human motion prediction. Previous methods mainly focus on dedicated …

Learning with auxiliary tasks can improve the ability of a primary task to generalise.
However, this comes at the cost of manually labelling auxiliary data. We propose a new …

Supervised machine learning techniques have already been widely studied and applied to
various real-world applications. However, most existing supervised algorithms work well …