.png){kind=icon}
返回
Multi-Task Learning for Audio-Based Infant Cry Detection and Reasoning
.png){kind=icon}
PRE
AI
DOI：10.1109/JBHI.2024.3454097.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Infant cry is a crucial indicator that offers valuable insights into their physical and mental conditions, such as hunger and pain. However, the scarcity of infant cry datasets hinders the model's generalization in real-life scenarios. The varying voiceprint characteristics among infants further exacerbate this challenge, deteriorating the model's performance on unseen infants. To this end, we propose a multi-task model for Infant Cry Detection and Reasoning (ICDR). It leverages datasets from two tasks to enrich data diversity and introduces an efficient attention module to achieve inter-task feature supplementarity. To mitigate the impact of subject differences, ICDR introduces an intra-task contrastive mixture of experts (CMoE) module that adaptively allocates experts to reduce subject variance and applies contrastive learning to enhance the representation consistency of samples from different infants in the same state. Extensive cross-subject experiments show that ICDR outperforms the state-of-the-art models in infant cry detection and reasoning, with an improvement of 2-9% in the F1-score. This demonstrates that multi-task learning effectively enhances the model's generalization ability by inter-task attention and intra-task CMoE.
Keyword:
Pediatrics
Task analysis
Feature extraction
Cognition
Multitasking
Support vector machines
Spectrogram
Audio
infant cry detection
infant cry reason classification
multi-task learning
期刊
IF:
6.8
论文数:
4.6K
被引数:
2.0W
机构
暂无机构信息
引用论文
Do Environmental Innovation and Green Energy Matter for Environmental Sustainability? Evidence from Saudi Arabia (1990–2018)环境创新和绿色能源对环境可持续性重要吗？来自沙特阿拉伯的证据 (1990-2018).png)
Energies
OAAI
EnergiesIF0
OAAI分享收藏A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity SensorsSENSORS
OAAI
SENSORSIF3.5
OAAI分享收藏分享收藏
查看更多内容