Target Speaker Isolation for Mobile Health Assessment From Speech With Crosstalk
Open Access
- 22 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 68186-68200
Abstract
Speech assessments are crucial for monitoring medical conditions such as Parkinson’s disease, depression, and Traumatic Brain Injury (TBI). However, crosstalk—speech from non-target speakers—presents a critical challenge in real-world mobile health assessments, often leading to false diagnoses. Continuous, real-world speech assessments using mobile devices are realistic but require additional pre-processing steps to ensure speech quality. Isolating the target speaker’s speech is necessary before health assessments. Previous research has focused on removing background noise but paid limited attention to crosstalk in passive health assessments. Some prior work addressed crosstalk using speech separation, which is found to create artifacts on the extracted speech. Instead, we propose Target Speaker Isolation with Normal Distribution (TSI-N) to isolate speech samples of the target speaker. Unlike standard embeddings, TSI-N utilizes an N-vector speaker representation trained to fit an unbounded normal distribution for each speaker cluster. This probabilistic property enables robust null-hypothesis testing and rapid online learning on resource-constrained mobile devices. In rigorous evaluations on various levels of crosstalk, TSI-N significantly outperforms state-of-the-art baselines, achieving accuracy improvements of up to 36% for TBI detection and 18% for depression detection in passive speech assessments.Keywords
Funding Information
- Defense Advanced Research Projects Agency (FA8750-18-2-0077)
- High-Performance Computing System acquired through the National Science Foundation Major Research Instrumentation (NSF MRI) Program (DMS-1337943)
This publication has 51 references indexed in Scilit:
- Speech as a Biomarker: Opportunities, Interpretability, and ChallengesPerspectives of the Asha Special Interest Groups, 2022
- MFCC-based Recurrent Neural Network for automatic clinical depression recognition and assessment from speechBiomedical Signal Processing and Control, 2022
- PowDroid: Energy Profiling of Android Applications2021
- Voxceleb: Large-scale speaker verification in the wildComputer Speech & Language, 2020
- Taking connected mobile-health diagnostics of infectious diseases to the fieldNature, 2019
- A deep transfer learning approach for improved post-traumatic stress disorder diagnosisKnowledge and Information Systems, 2019
- Smartphone-based passive assessment of mobility in depression: Challenges and opportunitiesMental Health and Physical Activity, 2018
- An Introduction to Application-Independent Evaluation of Speaker Recognition Systems2007
- Overlap in Meetings: ASR Effects and Analysis by Dialog Factors, Speakers, and Collection Site2006
- Conversational discourse in closed-head-injured and non-brain-injured adultsAphasiology, 2002