Acoustic Scene Classification Using Reduced MobileNet Architecture

Xu, Junxiang; Lin, Tzu-Ching; Yu, Tsai-Ching; Tai, Tzu-Chiang; Chang, Pao-Chi

doi:10.1109/ism.2018.00038

Cited by 11 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural networks (CNNs) are widely used in image recognition, speech recognition, and other fields, because they can learn different scales of interrelated features from input data based on mechanisms similar to the human brain. Among all available CNN models, ResNet, EfficientNet, MobileNet, and DenseNet are very representative and have been widely used in sound recognition [25,[41][42][43]; ResNet18, ResNet34, DenseNet_BC_34, MobileNet_v2, and EfficientNet_b3 were selected for performance comparison.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…On this basis, we used different deep learning models to learn these acoustic scene samples and compared the classification performance of different models, and we further analyzed the requirements of different models on the amount of training data and the number of training epochs. In terms of models, since deep learning models such as ResNet, DenseNet, MobileNet, and EfficientNet are very representative and have been widely used in the field of sound recognition [25,[40][41][42], we used ResNet18, ResNet34, DenseNet_BC_34, MobileNet_v2, and EfficientNet_b3 to classify the acoustic scene, respectively. The specific contributions and innovations of this paper are summarized as follows: (1) By converting the classification problem of different acoustic scenes into an image recognition problem, this study proposes the DenseNet_BC_34 model to achieve the accurate recognition of seven types of acoustic scene categories; (2) The innovative construction of an acoustic scene dataset for analyzing the correlation between human and animal sounds, containing seven types of acoustic scene data with a total of 7000 samples; (3) We analyzed and compared the classification performance of ResNet18, ResNet34, DenseNet_BC_34, MobileNet_v2, and EfficientNet_b3 models on the proposed acoustic scene categories under different training data amounts and different training epochs and explored the generalization performance of different models to new data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models

Zhang

Zhan

Hao

et al. 2023

Forests

View full text Add to dashboard Cite

The use of passive acoustic monitoring (PAM) can compensate for the shortcomings of traditional survey methods on spatial and temporal scales and achieve all-weather and wide-scale assessment and prediction of environmental dynamics. Assessing the impact of human activities on biodiversity by analyzing the characteristics of acoustic scenes in the environment is a frontier hotspot in urban forestry. However, with the accumulation of monitoring data, the selection and parameter setting of the deep learning model greatly affect the content and efficiency of sound scene classification. This study compared and evaluated the performance of different deep learning models for acoustic scene classification based on the recorded sound data from Guangzhou urban forest. There are seven categories of acoustic scenes for classification: human sound, insect sound, bird sound, bird–human sound, insect–human sound, bird–insect sound, and silence. A dataset containing seven acoustic scenes was constructed, with 1000 samples for each scene. The requirements of the deep learning models on the training data volume and training epochs in the acoustic scene classification were evaluated through several sets of comparison experiments, and it was found that the models were able to achieve satisfactory accuracy when the training sample data volume for a single category was 600 and the training epochs were 100. To evaluate the generalization performance of different models to new data, a small test dataset was constructed, and multiple trained models were used to make predictions on the test dataset. All experimental results showed that the DenseNet_BC_34 model performs best among the comparison models, with an overall accuracy of 93.81% for the seven acoustic scenes on the validation dataset. This study provides practical experience for the application of deep learning techniques in urban sound monitoring and provides new perspectives and technical support for further exploring the relationship between human activities and biodiversity.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models

Zhang

Zhan

Hao

et al. 2023

Forests

View full text Add to dashboard Cite

show abstract

“…Specifically, L-mHP is a three-channel feature composed of the Log-Mel spectrogram, harmonic spectrogram, and percussive spectrogram. The harmonic spectrogram and the percussive spectrogram are obtained by harmonic percussive source separation (HPSS) [23] of the Log-Mel spectrogram. Each channel of this feature focuses on different spectral characteristics of sound and are complementary to each other.…”

Section: L-mhp Feature Extraction Schemementioning

confidence: 99%

Environmental Sound Classification Framework Based on L-mHP Features and SE-ResNet50 Network Model

et al. 2023

View full text Add to dashboard Cite

Environmental sound classification (ESC) tasks are attracting more and more attention. Due to the complexity of the scene and personnel mobility, there are some difficulties in understanding and generating environmental sound models for ESC tasks. To address these key issues, this paper proposes an audio classification framework based on L-mHP features and the SE-ResNet50 model and improves a dual-channel data enhancement scheme based on a symmetric structure for model training. Firstly, this paper proposes the L-mHP feature to characterize environmental sound. The L-mHP feature is a three-channel feature consisting of a Log-Mel spectrogram, a harmonic spectrogram, and a percussive spectrogram. The harmonic spectrogram and percussive spectrogram can be obtained by harmonic percussive source separation (HPSS) of a Log-Mel spectrogram. Then, an improved audio classification model SE-ResNet50 is proposed based on the ResNet-50 model. In this paper, a dual-channel data enhancement scheme based on a symmetric structure is promoted, which not only makes the audio variants more diversified, but also makes the model focus on learning the time–frequency mode in the acoustic features during the training process, so as to improve the generalization performance of the model. Finally, the audio classification experiment of the framework is carried out on public datasets. An experimental accuracy of 94.92%, 99.67%, and 90.75% was obtained on ESC-50, ESC-10 and UrbanSound8K datasest, respectively. In order to simulate the classification performance of the framework in the actual environment, the framework was also evaluated on a self-made sound dataset with different signal-to-noise ratios. The experimental results show that the proposed audio classification framework has good robustness and feasibility.

show abstract

“…The first group of data augmentation algorithms generates new training data instances from existing ones by applying various signal transformations. Basic audio signal transformation includes time stretching, pitch shifting, dynamic range compression, as well as adding random noise [41][42][43]. Koutini et al applied spectral rolling by randomly shifting spectrogram excerpts over time [44].…”

Section: Data Augmentation Techniquesmentioning

confidence: 99%

A Review of Deep Learning Based Methods for Acoustic Scene Classification

Abeßer

2020

Applied Sciences

129

View full text Add to dashboard Cite

The number of publications on acoustic scene classification (ASC) in environmental audio recordings has constantly increased over the last few years. This was mainly stimulated by the annual Detection and Classification of Acoustic Scenes and Events (DCASE) competition with its first edition in 2013. All competitions so far involved one or multiple ASC tasks. With a focus on deep learning based ASC algorithms, this article summarizes and groups existing approaches for data preparation, i.e., feature representations, feature pre-processing, and data augmentation, and for data modeling, i.e., neural network architectures and learning paradigms. Finally, the paper discusses current algorithmic limitations and open challenges in order to preview possible future developments towards the real-life application of ASC systems.

show abstract

Acoustic Scene Classification Using Reduced MobileNet Architecture

Cited by 11 publications

References 4 publications

Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models

Classification of Complicated Urban Forest Acoustic Scenes with Deep Learning Models

Environmental Sound Classification Framework Based on L-mHP Features and SE-ResNet50 Network Model

A Review of Deep Learning Based Methods for Acoustic Scene Classification

Contact Info

Product

Resources

About