用小鼠叫声自动识别自闭症，首次将语音技术用于生物医学研究
MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge
- 基于三种频谱特征的简单卷积网络分类
- 可听频段特征在片段和个体级别分别达60%和62.5%准确率
- 适合语音分析与自闭症动物模型研究者参考
MADUV挑战赛是首个聚焦于通过小鼠超声发声检测自闭症谱系障碍（ASD）的INTERSPEECH竞赛。参赛者需开发模型，基于高采样率录音，自动区分野生型与自闭症模型小鼠。基线系统采用基于CNN的分类方法，使用三种不同频谱特征。结果表明自动化检测具有可行性，所考虑的可听频段特征表现最佳，片段级分类的均匀准确率（UAR）为0.600，个体级为0.625。该挑战连接了语音技术和生物医学研究，为利用机器学习推进自闭症模型理解提供了新路径。研究结果提示了发声分析的前景，并强调了可听及超声发声在自闭症检测中的潜在价值。
原文摘要 · Abstract (English)
The Mice Autism Detection via Ultrasound Vocalization (MADUV) Challenge introduces the first INTERSPEECH challenge focused on detecting autism spectrum disorder (ASD) in mice through their vocalizations. Participants are tasked with developing models to automatically classify mice as either wild-type or ASD models based on recordings with a high sampling rate. Our baseline system employs a simple CNN-based classification using three different spectrogram features. Results demonstrate the feasibility of automated ASD detection, with the considered audible-range features achieving the best performance (UAR of 0.600 for segment-level and 0.625 for subject-level classification). This challenge bridges speech technology and biomedical research, offering opportunities to advance our understanding of ASD models through machine learning approaches. The findings suggest promising directions for vocalization analysis and highlight the potential value of audible and ultrasound vocalizations in ASD detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。