SnoreFlowNet: Snore-Intensity and Airflow Dynamics Along with Cardiovascular Modalities for Deep Learning Based Sleep Apnea Detection
Bibliographic details pending final verification
Research area
Sleep Apnea & Respiratory AI
Learning from snoring, tracheal audio and physiological signals to detect respiratory events and support sleep-apnea screening.
Signals
SnoringTracheal audioAirflowSpO₂ECGPPGThoraxAbdomen
Models
CNNsTransformersWav2Vec2WhisperWavLM
Research questions
How can screening become less intrusive?
Which signals add complementary information?
How robust are models outside one device or cohort?
Related projects
Multimodal Sleep Apnea Screening
A research pipeline that combines respiratory acoustics and physiological dynamics for OSA screening.
Full-night Tracheal Audio Event Modelling
Full-night acoustic representation learning for localising apnea–hypopnea events and estimating burden.
Related publications
A Review on Speech as Biomarker for Obstructive Sleep Apnea (OSA)
Bibliographic details pending final verification