Sensing of inspiration events from speech: comparison of deep learning and linguistic methods

TL;DR

This study compares deep learning-based VRB algorithms and linguistic methods for detecting inspiration events from speech, demonstrating the superiority of neural VRB in identifying breathing patterns and providing new insights into speech breathing behavior.

Contribution

The paper introduces a novel neural VRB algorithm and VRBOLA for reconstructing breathing waveforms, advancing speech breathing analysis beyond linguistic segmentation methods.

Findings

VRB method outperforms word pause detection in inspiration event detection

Both read and spontaneous speech contain ungrammatical breathing events

New VRBOLA method effectively reconstructs continuous breathing waveforms

Abstract

Respiratory chest belt sensor can be used to measure the respiratory rate and other respiratory health parameters. Virtual Respiratory Belt, VRB, algorithms estimate the belt sensor waveform from speech audio. In this paper we compare the detection of inspiration events (IE) from respiratory belt sensor data using a novel neural VRB algorithm and the detections based on time-aligned linguistic content. The results show the superiority of the VRB method over word pause detection or grammatical content segmentation. The comparison of the methods show that both read and spontaneous speech content has a significant amount of ungrammatical breathing, that is, breathing events that are not aligned with grammatically appropriate places in language. This study gives new insights into the development of VRB methods and adds to the general understanding of speech breathing behavior. Moreover, a new VRB method, VRBOLA, for the reconstruction of the continuous breathing waveform is demonstrated.