Sound Tagging in Infant-centric Home Soundscapes
Mohammad Nur Hossain Khan, Jialu Li, Nancy L. McElwain, Mark, Hasegawa-Johnson, and Bashima Islam

TL;DR
This study investigates the effectiveness of large pre-trained models for classifying infant-centric environmental sounds in home settings, using a new dataset collected from infants' wearable devices and various training strategies.
Contribution
It introduces a novel infant-centric sound dataset collected via wearable devices and evaluates the performance of a large pre-trained model on this data, demonstrating improved classification accuracy.
Findings
Fine-tuning with combined datasets boosts F1-score to 0.84.
Using infant-centric data significantly improves model performance.
Data augmentation strategies enhance noise event detection accuracy.
Abstract
Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant's position or vice versa. Thus, despite the recent success of large pre-trained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInfant Health and Development
MethodsSoftmax · Layer Normalization · Byte Pair Encoding · Label Smoothing · Position-Wise Feed-Forward Layer · Dropout · Adam · Attention Is All You Need · Linear Layer · Absolute Position Encodings
