Real-Time Baby Crying Detection in the Noisy Everyday Environment

Foo, Lee Sze; Yap, Wun‐She; Hum, Yan Chai; Kadim, Zulaikha; Hon, Hock Woon; Tee, Yee Kai

doi:10.1109/icsgrc49013.2020.9232488

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using 30 epochs and batch size 256 , the F1 score obtained is 1 (accuracy =99.59%) while the proposed system in [5] achieves F1 score 0.613 in detecting the cry events per second using same dataset. Our system outperforms the approaches proposed in [6], [7] and [8] achieving (89.2 %, 90 % and 98.8%) using different datasets.…”

Section: Cry Detection Stagementioning

confidence: 70%

“…The machine learning model that makes use of both deep spectrum and acoustic information achieves the best F1 score 0.613 .They applied continuous signal segmenting using sliding window, The prediction for each second was labelled "crying" if it appeared in any sliding window of 1 sec containing that second. In [6] L.Sze et al proposed algorithm to detect cry in real noisy environment depending on acoustic features. Five acoustic features ; average frequency, pitch frequency, short-time energy (STE) acceleration, zero-crossing rate (ZCR), and Mel-Frequency cepstral coefficients (MFCC).…”

Section: Literature Review (Recent First)mentioning

confidence: 99%

“…Using noisy crying and non-crying samples, the algorithm was tested, and an accuracy of 89.20% was achieved for the offline testing. Also, three specially created noisy samples that included both crying and non-crying segments were used in [6] in online tests. The online accuracy was 80.77%.…”

Section: Literature Review (Recent First)mentioning

confidence: 99%

See 2 more Smart Citations

Infant Cry Signal Detection And Classification Using Deep Learning

eldine,

Ghanem,

Selim

et al. 2023

World Congress on Electrical Engineering and Computer Systems and Science

View full text Add to dashboard Cite

Detection of infant cries in noisy environments such as homes, hospitals and clinics is vital to determine the reason of baby's cry. Also, It is crucial to classify the detected cry signals into normal or pathological cries especially in the first months of the baby life. This paper proposes a deep learning automatic infant cry detection and classification system under noisy conditions. It classifies the detected cry signals into normal , asphyxia and deaf cry signals . The overall system is composed of two stages ; cry detection stage and cry classification stage. In first stage, features(Mel-frequency cepstrum coefficients MFCC) are extracted from audio signals collected from a daily life dataset and passed into a 2D-two layers convolutional neural network(2DCNN) to be classified into cry and non cry signals. In second stage , a 2D-three layers CNN is used to classify cry signals collected from dataset with cry segments only into Normal (N) , Asphyxia (A) and Deaf (D) signals according to extracted MFCC features . In first stage, Testing results show that the cry detection system reaches an accuracy of 99.59 % for classifying the signals into cry and non-cry . In second stage, Due to the lack of pathological cry signals datasets that are collected in noisy environments, we added different levels of white noise to the training dataset. This way, we were able to get more realistic results. In particular, our cry classification system achieves accuracy of 91.3% ,94.2% , 95.07 % (under white noise) with signal-to-noise ratio(SNR) of 5db, 10db and 15db, respectively.

show abstract