research
∙
09/14/2023
SpatialCodec: Neural Spatial Speech Coding
In this work, we address the challenge of encoding speech captured by a ...
share
research
∙
03/25/2023
Backdoor Attacks with Input-unique Triggers in NLP
Backdoor attack aims at inducing neural models to make incorrect predict...
research
∙
02/16/2023
PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
Despite rapid advancement in recent years, current speech enhancement mo...
research
∙
02/16/2023
TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement
Speech enhancement models have greatly progressed in recent years, but s...
research
∙
10/27/2022
Simulating realistic speech overlaps improves multi-talker ASR
Multi-talker automatic speech recognition (ASR) has been studied to gene...
research
∙
07/11/2022
Online Continual Learning of End-to-End Speech Recognition Models
Continual Learning, also known as Lifelong Learning, aims to continually...
research
∙
07/01/2022
Improving Speech Enhancement through Fine-Grained Speech Characteristics
While deep learning based speech enhancement systems have made rapid pro...
research
∙
07/17/2021
M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
Multimodal sentiment analysis aims to recognize people's attitudes from ...
research
∙
06/05/2021
Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
Deep neural networks have been shown as a class of useful tools for addr...
research
∙
03/21/2021
Self-supervised Representation Learning with Relative Predictive Coding
This paper introduces Relative Predictive Coding (RPC), a new contrastiv...
research
∙
07/27/2020
Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Diabetic Retinopathy (DR) is a leading cause of blindness in working age...
research
∙
04/29/2020
Interpretable Multimodal Routing for Human Multimodal Language
The human language has heterogeneous sources of information, including t...
research
∙
10/22/2019
Complex Transformer: A Framework for Modeling Complex-Valued Sequence
While deep learning has received a surge of interest in a variety of fie...
research
∙
04/21/2019