SVD-based redundancy removal in 1-D CNNs for acoustic scene classification

Singh, Arshdeep; Rajan, P.K.; Bhavsar, Arnav

doi:10.1016/j.patrec.2020.02.004

Cited by 14 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three modified CNN [30,32,33], Resnet based CNN [29] and Four-pathway residual CNNs [31], which use log Mel spectrograms, delta and delta-delta features, are other proposed classification methods. Optimized CNN [4], Fully CNN [34], Light CNN (LCNN) [35], DNN [36,56], VGG16 based CNN [37], SoundNet [39] and Front-end DNN + SVM [40] are among different classification schemes that have been used with hybrid features or RAW data in ASC. Based on the above review, one can conclude that many CNNs, DNNs and other deep learning classification methods have been suggested for ASC.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…These first and second log-Mel spectrogram derivatives are known as delta and delta-delta features. Log-Mel energies [4], log-Mel filter bank (LMFB) [34,35], log-Mel band energies and Single Frequency Filtering Cepstral Coefficients (SFFCC) [36] and MFCC and log-Mel filter bank [37] are other types of Mel-based features that have been used for ASC.…”

Section: Feature Extraction and Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Hajihashemi

Gharahbagh

Cruz³

et al. 2022

Sensors

View full text Add to dashboard Cite

The analysis of ambient sounds can be very useful when developing sound base intelligent systems. Acoustic scene classification (ASC) is defined as identifying the area of a recorded sound or clip among some predefined scenes. ASC has huge potential to be used in urban sound event classification systems. This research presents a hybrid method that includes a novel mathematical fusion step which aims to tackle the challenges of ASC accuracy and adaptability of current state-of-the-art models. The proposed method uses a stereo signal, two ensemble classifiers (random subspace), and a novel mathematical fusion step. In the proposed method, a stable, invariant signal representation of the stereo signal is built using Wavelet Scattering Transform (WST). For each mono, i.e., left and right, channel, a different random subspace classifier is trained using WST. A novel mathematical formula for fusion step was developed, its parameters being found using a Genetic algorithm. The results on the DCASE 2017 dataset showed that the proposed method has higher classification accuracy (about 95%), pushing the boundaries of existing methods.

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Section: Feature Extraction and Preprocessingmentioning

confidence: 99%

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Hajihashemi

Gharahbagh

Cruz³

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Medhat et al suggested masked CNN on used ESC datasets to get high accuracy in [51]. Singh et al narrated a method of using a single value decomposition method in one dimensional CNN for ESC-50 and attained remarkable results, as explained in [52]. Abdoli et al [53] has also implied 1-D CNN for Us8k with an accuracy of 89%.…”

Section: Related Workmentioning

confidence: 99%

Efficient Classification of Environmental Sounds through Multiple Features Aggregation and Data Enhancement Techniques for Spectrogram Images

Mushtaq

2020

Symmetry

View full text Add to dashboard Cite

Over the past few years, the study of environmental sound classification (ESC) has become very popular due to the intricate nature of environmental sounds. This paper reports our study on employing various acoustic features aggregation and data enhancement approaches for the effective classification of environmental sounds. The proposed data augmentation techniques are mixtures of the reinforcement, aggregation, and combination of distinct acoustics features. These features are known as spectrogram image features (SIFs) and retrieved by different audio feature extraction techniques. All audio features used in this manuscript are categorized into two groups: one with general features and the other with Mel filter bank-based acoustic features. Two novel and innovative features based on the logarithmic scale of the Mel spectrogram (Mel), Log (Log-Mel) and Log (Log (Log-Mel)) denoted as L2M and L3M are introduced in this paper. In our study, three prevailing ESC benchmark datasets, ESC-10, ESC-50, and Urbansound8k (Us8k) are used. Most of the audio clips in these datasets are not fully acquired with sound and include silence parts. Therefore, silence trimming is implemented as one of the pre-processing techniques. The training is conducted by using the transfer learning model DenseNet-161, which is further fine-tuned with individual optimal learning rates based on the discriminative learning technique. The proposed methodologies attain state-of-the-art outcomes for all used ESC datasets, i.e., 99.22% for ESC-10, 98.52% for ESC-50, and 97.98% for Us8k. This work also considers real-time audio data to evaluate the performance and efficiency of the proposed techniques. The implemented approaches also have competitive results on real-time audio data.

show abstract

“…Typically, CNNs have redundant parameters such as weights or filters, which yield only extra computations and storage without contributing much to the performance of the underlying task [3,4]. For example, Singh et al [5,6] found that 73% of the filters in SoundNet that do not provide discriminative information across different acoustic scene classes, and eliminating such filters gives similar performance compared to that of using all filters in SoundNet. Thus, the compression of CNNs has recently drawn significant attention from the research community.…”

Section: Introductionmentioning

confidence: 99%

Efficient Similarity-Based Passive Filter Pruning for Compressing CNNS

Singh

Plumbley

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Convolution neural networks (CNNs) have shown great success in various applications. However, the computational complexity and memory storage of CNNs is a bottleneck for their deployment on resource-constrained devices. Recent efforts towards reducing the computation cost and the memory overhead of CNNs involve similarity-based passive filter pruning methods. Similarity-based passive filter pruning methods compute a pairwise similarity matrix for the filters and eliminate a few similar filters to obtain a small pruned CNN. However, the computational complexity of computing the pairwise similarity matrix is high, particularly when a convolutional layer has many filters. To reduce the computational complexity in obtaining the pairwise similarity matrix, we propose to use an efficient method where the complete pairwise similarity matrix is approximated from only a few of its columns by using a Nyström approximation method. The proposed efficient similaritybased passive filter pruning method is 3 times faster and gives same accuracy at the same reduction in computations for CNNs compared to that of the similarity-based pruning method that computes a complete pairwise similarity matrix. Apart from this, the proposed efficient similarity-based pruning method performs similarly or better than the existing norm-based pruning methods. The efficacy of the proposed pruning method is evaluated on CNNs such as DCASE 2021 Task 1A baseline network and a VGGish network designed for acoustic scene classification.

show abstract

SVD-based redundancy removal in 1-D CNNs for acoustic scene classification

Cited by 14 publications

References 3 publications

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Binaural Acoustic Scene Classification Using Wavelet Scattering, Parallel Ensemble Classifiers and Nonlinear Fusion

Efficient Classification of Environmental Sounds through Multiple Features Aggregation and Data Enhancement Techniques for Spectrogram Images

Efficient Similarity-Based Passive Filter Pruning for Compressing CNNS

Contact Info

Product

Resources

About