Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet

Li, Yanxiong; Cao, Wenchang; Xie, Wei; Huang, Qisheng; Pang, Wenfeng; He, Qianhua

doi:10.1109/icsp56322.2022.9965347

Cited by 6 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ResNet is widely used as a backbone network for classifying acoustic scenes and has demonstrated superior performance [ 10 , 11 , 12 , 13 ]. Hence, we adopted the reduced ResNet-18 model, considering the lack of memory and long training time [ 22 , 38 , 44 ].…”

Section: Methodsmentioning

confidence: 99%

“…To use the superior discriminative power of deep neural networks, deep-learning-based methods have been proposed for ASC tasks and have shown better classification performance than traditional methods. Most deep-learning-based methods use the convolutional neural network (CNN) architecture, and ResNet [ 9 ] is widely used as a backbone network in CNNs because of its high classification accuracy [ 10 , 11 , 12 , 13 , 50 ].…”

Section: Related Workmentioning

confidence: 99%

“…Acoustic scene classification (ASC) involves classifying a sound event into a predefined acoustic scene class [ 1 , 2 , 3 , 4 ]. Because deep-learning-based methods significantly improve performance in various tasks, numerous deep learning methods have been applied to ASC tasks to improve the classification accuracy of sound events [ 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 ]. In the detection and classification of acoustic scenes and events (DCASE) challenge, which is a representative event in the field of ASC, deep-learning-based methods improved the performance of sound event classification [ 10 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Online Continual Learning in Acoustic Scene Classification: An Empirical Study

Kim

Jeong

2023

Sensors

View full text Add to dashboard Cite

Numerous deep learning methods for acoustic scene classification (ASC) have been proposed to improve the classification accuracy of sound events. However, only a few studies have focused on continual learning (CL) wherein a model continually learns to solve issues with task changes. Therefore, in this study, we systematically analyzed the performance of ten recent CL methods to provide guidelines regarding their performances. The CL methods included two regularization-based methods and eight replay-based methods. First, we defined realistic and difficult scenarios such as online class-incremental (OCI) and online domain-incremental (ODI) cases for three public sound datasets. Then, we systematically analyzed the performance of each CL method in terms of average accuracy, average forgetting, and training time. In OCI scenarios, iCaRL and SCR showed the best performance for small buffer sizes, and GDumb showed the best performance for large buffer sizes. In ODI scenarios, SCR adopting supervised contrastive learning consistently outperformed the other methods, regardless of the memory buffer size. Most replay-based methods have an almost constant training time, regardless of the memory buffer size, and their performance increases with an increase in the memory buffer size. Based on these results, we must first consider GDumb/SCR for the continual learning methods for ASC.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online Continual Learning in Acoustic Scene Classification: An Empirical Study

Kim

Jeong

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, due to the complex algorithm design of Gaussian mixture model (GMM) and hidden Markov model (HMM), and the difficulty in selecting appropriate features in unknown scenarios [7,8], it may not be suitable for the recognition and classification of abnormal sound data. On the contrary, deep learning models like CNNs, RNNs, LSTMs, TDNNs, and ResNets [9][10][11][12][13] have gained popularity. Vafeiadis [14] demonstrates that two-dimensional Convolutional Neural Networks (2D CNNs) using Mel-spectrograms as input features exhibit excellent identification capabilities.…”

Section: Introductionmentioning

confidence: 99%

Combined Data Augmentation on EANN to Identify Indoor Anomalous Sound Event

Song,

Xiong,

Wang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Indoor abnormal sound event identification refers to the automatic detection and recognition of abnormal sounds in an indoor environment using computer auditory technology. However, the process of model training usually requires a large amount of high-quality data, which can be time-consuming and costly to collect. Utilizing limited data has become another preferred approach for such research, but it introduces overfitting issues for machine learning models on small datasets. To overcome this issue, we proposed and validated the framework of combining the offline augmentation of raw audio and online augmentation of spectral features, making the application of small datasets in indoor anomalous sound event identification more feasible. Along with this, an improved two-dimensional audio convolutional neural network (EANN) was also proposed to evaluate and compare the impacts of different data augmentation methods under the framework on the sensitivity of sound event identification. Moreover, we further investigated the performance of four combinations of data augmentation techniques. Our research shows that the proposed combined data augmentation method has an accuracy of 97.4% on the test dataset, which is 10.6% higher than the baseline method. This demonstrates the method’s potential in the identification of indoor abnormal sound events.

show abstract