Picture for Meishu Song

Meishu Song

Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts

Add code
Sep 27, 2022
Figure 1 for Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts
Figure 2 for Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts
Figure 3 for Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts
Viaarxiv icon

Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression

Add code
Jun 28, 2022
Figure 1 for Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression
Figure 2 for Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression
Figure 3 for Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regression
Viaarxiv icon

Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression

Add code
Jun 27, 2022
Figure 1 for Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression
Figure 2 for Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expression
Viaarxiv icon

COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection

Add code
Jun 20, 2022
Figure 1 for COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection
Figure 2 for COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection
Figure 3 for COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection
Figure 4 for COVYT: Introducing the Coronavirus YouTube and TikTok speech dataset featuring the same speakers with and without infection
Viaarxiv icon

Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction

Add code
Jun 20, 2022
Figure 1 for Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction
Figure 2 for Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction
Viaarxiv icon

A Temporal-oriented Broadcast ResNet for COVID-19 Detection

Add code
Mar 31, 2022
Figure 1 for A Temporal-oriented Broadcast ResNet for COVID-19 Detection
Figure 2 for A Temporal-oriented Broadcast ResNet for COVID-19 Detection
Figure 3 for A Temporal-oriented Broadcast ResNet for COVID-19 Detection
Figure 4 for A Temporal-oriented Broadcast ResNet for COVID-19 Detection
Viaarxiv icon

An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion

Add code
Mar 29, 2022
Figure 1 for An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion
Viaarxiv icon

An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety

Add code
May 14, 2020
Figure 1 for An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
Figure 2 for An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
Figure 3 for An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
Figure 4 for An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety
Viaarxiv icon