Detection of speech events and speaker characteristics through photo-plethysmographic signal neural processing

TL;DR

This paper investigates the use of convolutional neural networks to extract human characteristics and speech events from photoplethysmogram signals, demonstrating promising results in biometric and speech detection tasks.

Contribution

It introduces novel end-to-end CNN architectures for extracting biometric and speech-related information from PPG signals, showing potential for low-cost, non-invasive biometric and speech analysis.

Findings

PPG signals can be used for gender and identity verification with high accuracy.

Speech detection from PPG signals achieved moderate success, indicating feasibility.

End-to-end neural networks effectively extract meaningful biomarkers from noisy PPG data.

Abstract

The use of photoplethysmogram signal (PPG) for heart and sleep monitoring is commonly found nowadays in smartphones and wrist wearables. Besides common usages, it has been proposed and reported that person information can be extracted from PPG for other uses, like biometry tasks. In this work, we explore several end-to-end convolutional neural network architectures for detection of human's characteristics such as gender or person identity. In addition, we evaluate whether speech/non-speech events may be inferred from PPG signal, where speech might translate in fluctuations into the pulse signal. The obtained results are promising and clearly show the potential of fully end-to-end topologies for automatic extraction of meaningful biomarkers, even from a noisy signal sampled by a low-cost PPG sensor. The AUCs for best architectures put forward PPG wave as biological discriminant, reaching $79\%$ and $89.0\%$, respectively for gender and person verification tasks. Furthermore, speech detection experiments reporting AUCs around $69\%$ encourage us for further exploration about the feasibility of PPG for speech processing tasks.