A Dynamic Parametric Simulator for Fetal Heart Sounds

TL;DR

This paper introduces a reproducible, dynamic parametric simulator for fetal heart sounds that synthesizes realistic abdominal recordings, aiding benchmarking and development of fetal phonocardiogram analysis methods.

Contribution

It presents a novel simulator combining cycle-level event synthesis with a transmission model, calibrated from real data, to generate realistic fetal heart sound sequences.

Findings

Simulator accurately reproduces temporal and frequency characteristics of real recordings

Enables controlled, reproducible testing of fetal phonocardiogram processing methods

Open-source software supports widespread adoption and benchmarking

Abstract

Research on fetal phonocardiogram (fPCG) is challenged by the limited number of abdominal recordings, substantial maternal interference, and marked transmissioninduced signal attenuation that complicate reproducible benchmarking. We present a reproducible dynamic parametric simulator that generates long abdominal fPCG sequences by combining cycle-level fetal S1/S2 event synthesis with a convolutional transmission module and configurable interference and background noise. Model parameters are calibrated cyclewise from real abdominal recordings to capture beat-to-beat variability and to define data-driven admissible ranges for controllable synthesis. The generated signals are validated against real recordings in terms of envelope-based temporal structure and frequency-domain characteristics. The simulator is released as open software to support rapid, reproducible evaluation of fPCG processing methods under controlled acquisition conditions.