1 code implementation • 15 Jul 2022 • Yang Xiao, Xubo Liu, James King, Arshdeep Singh, Eng Siong Chng, Mark D. Plumbley, Wenwu Wang
Experimental results on the DCASE 2019 Task 1 and ESC-50 dataset show that our proposed method outperforms baseline continual learning methods on classification accuracy and computational efficiency, indicating our method can efficiently and incrementally learn new classes without the catastrophic forgetting problem for on-device environmental sound classification.
1 code implementation • 30 May 2023 • Arshdeep Singh, Haohe Liu, Mark D. Plumbley
Sounds carry an abundance of information about activities and events in our everyday environment, such as traffic noise, road works, music, or people talking.
1 code implementation • 15 Jun 2023 • Gabriel Bibbo, Arshdeep Singh, Mark D. Plumbley
In this paper, we analyze how the performance of large-scale pretrained audio neural networks designed for audio pattern recognition changes when deployed on a hardware such as Raspberry Pi.
1 code implementation • 27 Oct 2022 • Arshdeep Singh, Mark D. Plumbley
However, the computational complexity of computing the pairwise similarity matrix is high, particularly when a convolutional layer has many filters.
no code implementations • 18 Jan 2019 • Mayank Singh Chauhan, Arshdeep Singh, Mansi Khemka, Arneish Prateek, Rijurekha Sen
Classifying and counting vehicles in road traffic has numerous applications in the transportation engineering domain.
1 code implementation • 28 Apr 2021 • Soumi Das, Arshdeep Singh, Saptarshi Chatterjee, Suparna Bhattacharya, Sourangshu Bhattacharya
In this paper, we study the problem of selecting high-value subsets of training data.
no code implementations • 21 Nov 2021 • Arshdeep Singh, Raju Arvind, Padmanabhan Rajan
In classification, our hypothesis is that the reconstruction error computed for an abnormal machine is larger than that of the a normal machine, since only normal machine sounds are being used to train the autoencoder.
1 code implementation • 29 Mar 2022 • Arshdeep Singh, Mark D. Plumbley
We propose a passive filter pruning framework, where a few convolutional filters from the CNNs are eliminated to yield compressed CNNs.
no code implementations • 31 Mar 2022 • Arshdeep Singh
This paper presents an alternate representation framework to commonly used time-frequency representation for acoustic scene classification (ASC).
no code implementations • 23 Jul 2022 • Arshdeep Singh, Mark D. Plumbley
However, CNNs are resource hungry due to their large size and high computational complexity.
no code implementations • 2 Aug 2022 • Arshdeep Singh, James A King, Xubo Liu, Wenwu Wang, Mark D. Plumbley
This technical report describes the SurreyAudioTeam22s submission for DCASE 2022 ASC Task 1, Low-Complexity Acoustic Scene Classification (ASC).
no code implementations • 5 Apr 2023 • Arshdeep Singh, Mark D. Plumbley
In comparison to the existing active filter pruning methods, the proposed pruning method is at least 4. 5 times faster in computing filter importance and is able to achieve similar performance compared to that of the active filter pruning methods.
no code implementations • 5 May 2023 • James A King, Arshdeep Singh, Mark D. Plumbley
For large-scale CNNs such as PANNs designed for audio tagging, our method reduces 24\% computations per inference with 41\% fewer parameters at a slight improvement in performance.
no code implementations • 30 Oct 2023 • Chris Richardson, Yao Zhang, Kellen Gillespie, Sudipta Kar, Arshdeep Singh, Zeynab Raeesy, Omar Zia Khan, Abhinav Sethy
To overcome these limitations, we propose a novel summary-augmented approach by extending retrieval-augmented personalization with task-aware user summaries generated by LLMs.