Fusing ASR Outputs in Joint Training for Speech Emotion Recognition

Li, Yuanchao; Bell, P. R. F.; Lai, Catherine

doi:10.48550/arxiv.2110.15684

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research on emotion recognition is becoming more and more popular, such as speech-based emotion recognition [21], textbased emotion recognition [22], multimodal emotion recognition [23,24] and action-based emotion recognition [25]. Previous studies have revealed that emotion can be reflected from action.…”

Section: Introductionmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Introductionmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…[4] evaluated several handcrafted feature sets designed for different computational paralinguistics tasks and proposed a novel Active Data Representation method using acoustic features of all arXiv:2211.08526v1 [cs.RO] 15 Nov 2022 speech segments with a single fixed-dimension feature vector. Inspired by successful end-to-end approaches in speech and emotion recognition [19], [20], some recent works extract features directly from log-mel spectrograms instead of using handcrafted ones, resulting in better performance [21], [22].…”

Section: Related Work a Ad Detection From Speechmentioning

confidence: 99%

Alzheimer's Dementia Detection through Spontaneous Dialogue with Proactive Robotic Listeners

Lai

Lala

et al. 2022

2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)

Self Cite

View full text Add to dashboard Cite

As the aging of society continues to accelerate, Alzheimer's Disease (AD) has received more and more attention from not only medical but also other fields, such as computer science, over the past decade. Since speech is considered one of the effective ways to diagnose cognitive decline, AD detection from speech has emerged as a hot topic. Nevertheless, such approaches fail to tackle several key issues: 1) AD is a complex neurocognitive disorder which means it is inappropriate to conduct AD detection using utterance information alone while ignoring dialogue information; 2) Utterances of AD patients contain many disfluencies that affect speech recognition yet are helpful to diagnosis; 3) AD patients tend to speak less, causing dialogue breakdown as the disease progresses. This fact leads to a small number of utterances, which may cause detection bias. Therefore, in this paper, we propose a novel AD detection architecture consisting of two major modules: an ensemble AD detector and a proactive listener. This architecture can be embedded in the dialogue system of conversational robots for healthcare.

show abstract

Fusing ASR Outputs in Joint Training for Speech Emotion Recognition

Cited by 2 publications

References 16 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

Alzheimer's Dementia Detection through Spontaneous Dialogue with Proactive Robotic Listeners

Contact Info

Product

Resources

About