Researchers release SpeechDx benchmark for clinical speech AI

Arxiv CS.SD (Sound/Audio ML)

SpeechDx provides a multi-task benchmark designed to unify isolated, condition-specific studies in clinical speech analysis. It addresses the challenge of integrating heterogeneous neurological, motor, and vocal data to improve neurodegenerative disease screening.

Speech recognition

See 8 more sources

Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation4 days agoReihaneh Amooie, Yun Hao, Wietse de Vries, Jelske Dijkstra, Matt Coler, Martijn Wieling

SpeechDx: A Multi-Task Benchmark for Clinical Speech AI5 days agoSejal Bhalla, Larry Kieu, Aina Merchant, Eyal de Lara, Alex Mariakakis

DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization5 days agoLiming Wang, Cody Karjadi, Rhoda Au, James Glass

Reading between the Lines: Leveraging Large Language Models for Global Dementia and Depression Assessment from Clinical Interviews5 days agoFranziska Braun, Alea R\"uggeberg, Thomas Ranzenberger, Hartmut Lehfeld, Thomas Hillemacher, Tobias Bocklet, Korbinian Riedhammer

Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening5 days agoQingfeng Zhang, Yuanxiong Guo, Yanmin Gong

Mitigating Scoring Errors and Compensating for Nonverbal Subtests in Speech-Based Dementia Assessment4 days agoFranziska Braun, Christopher Witzl, Andreas Erzigkeit, Hartmut Lehfeld, Thomas Hillemacher, Tobias Bocklet, Korbinian Riedhammer

Decoding while Adapting: Zero-Shot Online Speaker Adaptation via Audio-Textual Prompts for Elderly Speech Recognition5 days agoChengxi Deng, Xurong Xie, Shujie Hu, Mengzhe Geng, Tianzi Wang, Youjun Chen, Huimeng Wang, Haoning Xu, Jiajun Deng, Xunying Liu

Confidence Score Guided Incremental and Speaker Adaptive Pseudo-Labeling for Semi-Supervised Elderly Speech Recognition5 days agoChengxi Deng, Xurong Xie, Shujie Hu, Jiajun Deng, Mengzhe Geng, Youjun Chen, Huimeng Wang, Haoning Xu, Guinan Li, Xunying Liu

Arxiv CS.SD (Sound/Audio ML)·William NguyenJiali ChengHadi Amiri

Jun 17, 4:00 AM