@InProceedings{Macintyre2023_1179,
author = {Alexis Deighton Macintyre and Raphael Werner},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2023},
title = {An Automatic Method for Speech Breathing Annotation},
year = {2023},
editor = {Christoph Draxler},
month = mar,
pages = {103--110},
publisher = {TUDpress, Dresden},
abstract = {Breathing is central to speech planning and production; however, speech
breathing is difficult to monitor and quantify without laborious and subjective manual
annotation. Here, we describe a method for automatically detecting the beginning
and end time points of speech-associated inhalations measured with inductive
plethysmography, or breath belts. Unlike simpler approaches to breath detection,
the technique introduced here employs slope analysis to improve temporal precision.
First, inhalation events are identified by searching for roughly continuous,
positive sloping segments. Inhalations are then rejected or modified based on slope
height, duration, and grade, as well as contextual factors, such as the height or duration
of neighbouring breaths. Finally, the respiratory time series can be optionally
corroborated with acoustic recordings to further improve results. This approach
is validated by two independent annotators using spontaneous and read English
speech contributed by 10 individual speakers, including relatively noisy data. From
a signal detection perspective, we estimate performance at 95% on average. The
mean median error of detected breaths, when compared to human annotation, is
22.50 ms (IQR 37.71 ms). By comparison, a peak-finding method without acoustic
calibration yields 91% accuracy with substantially larger errors (mean median
167.90 ms, IQR 381.45 ms). In conclusion, the proposed automatic method provides
robust and temporally accurate annotation of the speech breathing time series.},
isbn = {978-3-95908-303-4},
issn = {0940-6832},
keywords = {Phonetics},
url = {https://www.essv.de/pdf/2023_103_110.pdf},
}