Pre-processing techniques for improved detection of vocalization sounds in a neonatal intensive care unit. (January 2018)

• Record Type: Journal Article
• Authors: Raboshchuk, Ganna; Nadeu, Climent; Vidiella Pinto, Sergio; Ros Fornells, Oriol; Muñoz Mahamud, Blanca; Riverola de Veciana, Ana
• Is Part Of: Biomedical signal processing and control. Volume 39(2018)
• Page Start: 390
• Page End: 395
• Publication Date: 2018-01
• Subjects: Neonatal intensive care unit -- Vocalization detection -- Noise reduction -- Spectral subtraction -- Non-negative matrix factorization; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.07.024
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Automatic analysis of the acoustic environment of a preterm infant in a NICU. New and challenging problem of vocalization detection in a NICU environment. Pre-processing techniques for non-vocalization sounds reduction. An audio database acquired in a real-world NICU environment. Abstract: The sounds occurring in the noisy acoustical environment of a Neonatal Intensive Care Unit (NICU) are thought to affect the growth and neurodevelopment of preterm infants. Automatic sound detection in a NICU is a novel and challenging problem, and it is an essential step in the investigation of how preterm infants react to auditory stimuli of the NICU environment. In this paper, we present our work on an automatic system for detection of vocalization sounds, which are extensively present in NICUs. The proposed system reduces the presence of irrelevant sounds prior to detection. Several pre-processing techniques are compared, which are based on either spectral subtraction or non-negative matrix factorization, or a combination of both. The vocalization sounds are detected from the enhanced audio signal using either generative or discriminative classification models. An audio database acquired in a real-world NICU environment is used to assess the performance of the detection system in terms of frame-level missing and false alarm rates. The inclusion of the enhancement pre-processing step leads to up to 17.54% relative improvement over the baseline.