168 citations · 523 across the 46 of their papers we have counts for
12 papers · 1 filter
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
Zijian Yang, Wei Zhou, Ralf Schlüter +1
Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obta…
Random Vector Representation of Continuous Functions and Its Applica-tions in Quantum Mechanics
Hong-Xing Li, Wei Zhou, Hong-Hai Mi
The relation between continuous functions and random vectors is revealed in the paper that the main meaning is described as, for any given continuous function, there must be a sequ…
Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Andrey Ignatov, Radu Timofte, Shuai Liu +35
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In thi…
Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning
Xiong Junwu, Xiaoyun Feng, YunZhou Shi +3
Digital human recommendation system has been developed to help customers find their favorite products and is playing an active role in various recommendation contexts. How to timel…
The crater-induced YORP effect
Wen-Han Zhou, Yun Zhang, Xiaoran Yan +1
The Yarkovsky-O'Keefe-Radzievskii-Paddack (YORP) effect plays an important role in the rotational properties and evolution of asteroids. While the YORP effect induced by the macros…
Ultrafast Switching in Synthetic Antiferromagnet with Bilayer Rare-Earth Transition-Metal Ferrimagnets
Chung Ting Ma, Wei Zhou, S. Joseph Poon
In spintronics, it is important to be able to manipulate magnetization rapidly and reliably. Several methods can control magnetization, such as by applying current pulses or magnet…
An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
Xiu-Shen Wei, He-Yang Xu, Faen Zhang +2
Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated metho…
FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications
Wei Zhou, Xuanlin Min, Rui Hu +3
Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes. T…
What Your Firmware Tells You Is Not How You Should Emulate It: A Specification-Guided Approach for Firmware Emulation (Extended Version)
Wei Zhou, Lan Zhang, Le Guan +2
Emulating firmware of microcontrollers is challenging due to the lack of peripheral models. Existing work finds out how to respond to peripheral read operations by analyzing the ta…
Multi-Granularity Semantic Aware Graph Model for Reducing Position Bias in Emotion-Cause Pair Extraction
Yinan Bao, Qianwen Ma, Lingwei Wei +2
The Emotion-Cause Pair Extraction (ECPE) task aims to extract emotions and causes as pairs from documents. We observe that the relative distance distribution of emotions and causes…
Efficient Training of Neural Transducer for Speech Recognition
Wei Zhou, Wilfried Michel, Ralf Schlüter +1
As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated ne…
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech
Guangyan Zhang, Kaitao Song, Xu Tan +8
Recently, leveraging BERT pre-training to improve the phoneme encoder in text to speech (TTS) has drawn increasing attention. However, the works apply pre-training with character-b…