Acoustic scene classification: A comprehensive survey

Ding, Biyun; Zhang, Tao; Wang, Chao; Liu, Ganjun; Liang, Jinhua; Hu, Ruimin; Wu, Yulin; Guo, Difei

doi:10.1016/j.eswa.2023.121902

Cited by 2 publications

(1 citation statement)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many of these works have achieved good or very good performance on multi-class classification, indicating that models can learn distinguishing acoustic features between individual sounds or groups of sounds. Early models used traditional machine learning techniques such as Support Vector Machines, Gaussian Mixture Models and K-Nearest Neighbours with extracted acoustic input features including mel-frequency cepstrum coefficients (MFCC), temporal, spectral, energy and prosodic features (51)(52)(53)(54)(55). However, currently, most state-of-theart models use deep learning techniques to classify sound events or scenes (56)(57)(58).…”

Section: Audio Classificationmentioning

confidence: 99%

Auditory chaos classification in real-world environments

Khante,

Thomaz,

de Barbaro

2023

Front. Digit. Health

View full text Add to dashboard Cite

Background & motivationHousehold chaos is an established risk factor for child development. However, current methods for measuring household chaos rely on parent surveys, meaning existing research efforts cannot disentangle potentially dynamic bidirectional relations between high chaos environments and child behavior problems.Proposed approachWe train and make publicly available a classifier to provide objective, high-resolution predictions of household chaos from real-world child-worn audio recordings. To do so, we collect and annotate a novel dataset of ground-truth auditory chaos labels compiled from over 411 h of daylong recordings collected via audio recorders worn by N=22 infants in their homes. We leverage an existing sound event classifier to identify candidate high chaos segments, increasing annotation efficiency 8.32× relative to random sampling.ResultOur best-performing model successfully classifies four levels of real-world household auditory chaos with a macro F1 score of 0.701 (Precision: 0.705, Recall: 0.702) and a weighted F1 score of 0.679 (Precision: 0.685, Recall: 0.680).SignificanceIn future work, high-resolution objective chaos predictions from our model can be leveraged for basic science and intervention, including testing theorized mechanisms by which chaos affects children’s cognition and behavior. Additionally, to facilitate further model development we make publicly available the first and largest balanced annotated audio dataset of real-world household chaos.

show abstract