TP-MobNet: A Two-pass Mobile Network for Low-complexity Classification of Acoustic Scene
Source abstract
Abstract
Acoustic scene classification (ASC) is a method of recognizing and classifying environments that employ acoustic signals. Various ASC approaches based on deep learning have been developed, with convolutional neural networks (CNNs) proving to be the most reliable and commonly utilized in ASC systems due to their suitability for constructing lightweight models. When using ASC systems in the real world, model complexity and device robustness are essential considerations. In this paper, we propose a two-pass mobile network for low-complexity classification of the acoustic scene, named TP-MobNet. With inverse residuals and linear bottlenecks, TP-MobNet is based on MobileNetV2, and following mobile blocks, coordinate attention and two-pass fusion approaches are utilized. The log-range dependencies and precise position information in feature maps can be trained via coordinate attention. By capturing more diverse feature resolutions at the network's end sides, two-pass fusions can also train generalization. Also, the model size is reduced by applying weight quantization to the trained model. By adding weight quantization to the trained model, the model size is also lowered. The TAU Urban Acoustic Scenes 2020 Mobile development set was used for all of the experiments. It has been confirmed that the proposed model, with a model size of 219.6 kB, achieves an accuracy of 73.94%.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Speech and Audio Processing · Underwater Acoustics Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (31)
Show source-provided references
1. Deep learning based audio scene classification
2. Deep neural networks for audio scene recognition
3. Improving the speed of neural networks on CPUs
4. A review of deep learning research
5. Environmental sound classification with convolutional neural networks
6. Acoustic scene classification using parallel combination of LSTM and CNN
7. Acoustic scene classification using convolutional recurrent neural networks
8. Convolutional neural network based audio event classification
9. DCASE 2016 acoustic scene classification using convolutional neural networks
10. Convolutional neural networks with binaural representations and background subtraction for acoustic scene classification
11. A. G. Howard, M. Zhu, B. Chen, D. Kalenicheonko, W. Wang et al., “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017.
12. Mobilenetv2: Inverted residuals and linear bottlenecks
13. ShuffleNet: An extremely efficient convolutional neural network for mobile devices
14. Device-robust acoustic scene classification based on two-stage categorization and data augmentation
15. Acoustic scene classification in DCASE 2020 challenge: Generalization across devices and low complexity solutions
16. A multi-device dataset for urban acoustic scene classification
17. A convolutional neural network approach for acoustic scene classification
18. Acoustic scene classification with fully convolutional neural network and i-vectors
19. Acoustic scene classification using lightweight ResNet with attention
20. Acoustic scene classification using deep residual network with late fusion of separated high and low frequency paths
21. Coordinate attention for efficient mobile network design
22. Squeeze-and-excitation networks
23. Quantization and training of neural networks for efficient integer-arithmetic-only inference
24. Google Inc. TensorFlow Lite. [Online]. Available: https://www. tensorflow.org/mobile/tflite, 2021.
25. H. Zhang, M. Cisse, Y. N. Dauphin and D. Lopez-Paz, “Mixup: Beyond empirical risk minimization,” arXiv preprint arXiv:1710.09412, 2017.
26. SpecAugment: A simple data augmentation method for automatic speech recognition
27. I. Martin-Morato, T. Heittola, A. Mesaros and T. Virtanen, “Low-complexity acoustic scene classification for multi-device audio: Analysis of DCASE 2021 challenge systems,” arXiv preprint arXiv:2105.13734, 2021.
28. Low-complexity acoustic scene classification using mobile inverted bottleneck blocks
29. Small-footprint acoustic scene classification through 8-bit quantization-aware training and pruning of ResNet models
30. Cpjku submission to decase21: Cross-device audio scene classification with wide sparse frequency-damped cnns
31. Shallow convolution-augmented transformer with differentiable neural computer for low-complexity classification of variable-length acoustic scene