Novel Phase Encoded Mel Filterbank Energies for Environmental Sound Classification

Tak, Rishabh; Agrawal, Dharmesh M.; Patil, Hemant A.

doi:10.1007/978-3-319-69900-4_40

Cited by 31 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second is an end-to-end method for dealing with raw audio data by using a shallow and wide raw feature extractor [46,47] rather than a Fourier transform. The third one uses improved learning techniques, such as data argumentation [47][48][49], pre-processing (or post-processing) [50,51], and other learning methods, such self (or weakly) supervised learning [10,[37][38][39][40][41]47,51].…”

Section: Audio Feature Extractionmentioning

confidence: 99%

“…In the initialization section, the hyper-parameters of the FFT were experimentally obtained based on values that are commonly used in ESC-50, and the hyper-parameters of the MTST were obtained via a greedy search. The ranges of the greedy searches were as follows: The steps were [50,100,150,200,250, 300] and x_size was [224,401,501,601,701,801]. M was a method of conversion from raw data into a mel-spectrogram with the conversion of power to decibels (dB).…”

Section: Audio Feature Extraction Via Multi-time-scale Transformmentioning

confidence: 99%

See 1 more Smart Citation

Construction of a Soundscape-Based Media Art Exhibition to Improve User Appreciation Experience by Using Deep Neural Networks

et al. 2021

View full text Add to dashboard Cite

The objective of this study was to improve user experience when appreciating visual artworks with soundscape music chosen by a deep neural network based on weakly supervised learning. We also propose a multi-faceted approach to measuring ambiguous concepts, such as the subjective fitness, implicit senses, immersion, and availability. We showed improvements in appreciation experience, such as the metaphorical and psychological transferability, time distortion, and cognitive absorption, with in-depth experiments involving 70 participants. Our test results were similar to those of “Bunker de Lumières: van Gogh”, which is an immersive media artwork directed by Gianfranco lannuzzi; the fitness scores of our system and “Bunker de Lumières: van Gogh” were 3.68/5 and 3.81/5, respectively. Moreover, the concordance of implicit senses between artworks and classical music was measured to be 0.88%, and the time distortion and cognitive absorption improved during the immersion. Finally, the proposed method obtained a subjective satisfaction score of 3.53/5 in the evaluation of its usability. Our proposed method can also help spread soundscape-based media art by supporting traditional soundscape design. Furthermore, we hope that our proposed method will help people with visual impairments to appreciate artworks through its application to a multi-modal media art guide platform.

show abstract

Section: Audio Feature Extractionmentioning

confidence: 99%

Section: Audio Feature Extraction Via Multi-time-scale Transformmentioning

confidence: 99%

Construction of a Soundscape-Based Media Art Exhibition to Improve User Appreciation Experience by Using Deep Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Accuracy(%) ESC-10 ESC-50 Human [34] 95.70 81.30 EnvNet-v2 [14] 88.80 81.6 ± 0.2 GSTC TEO-GSTC [54] -81.95 GTSC ConvRBM-BANK [12] -83.00 Kumar-CNN [55] -83.50 CNN+Augment+Mixup [56] 91.70 83.90 Multi-stream+Attention [57] 94.20 84.00 FBEs PEFBEs [58] -84.15 EnvNet-v2 [14] Few state-of-the-art models report their size and computation requirements in the literature. According to our knowledge on current literature, EnvNet-v2 and AclNet are the only two of the top-ten models for either of the two datasets to report parameter count, size, and FLOPs.…”

Section: Networkmentioning

confidence: 99%

Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices

Mohaimenuzzaman,

Bergmeir,

West

et al. 2021

Preprint

View full text Add to dashboard Cite

We introduce the first ever pipeline for sound classification using Deep Learning in extremely resource-constrained (battery powered, low memory and CPU speed) microcontrollers (MCUs).• Firstly, we present a CNN architecture (ACDNet) that achieves stateof-the-art classification accuracy on ESC-10 and ESC-50 benchmark datasets.• Secondly, we compress ACDNet using our proposed hybrid structured compression technique to obtain Micro-ACDNet that is 97.22% smaller in size and requires 97.28% less FLOPs yet produces close to state-ofthe-art performance.• Finally, after 8-bit quantization, we deploy Micro-ACDNet on a standard off-the shelf MCU.

show abstract

“…Since DCT is a linear transform, some information in highly non-linear speech signals will be discarded undesirably. For this reason, MFBE is becoming increasingly popular due to rapid growth of endto-end techniques using deep learning, because it can provide more information than MFCC for neural networks to delve into [15], [16], [42].…”

Section: Acoustic Featurementioning

confidence: 99%

Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker Verification

Yao,

Chen,

Cui

et al. 2020

Preprint

View full text Add to dashboard Cite

Novel Phase Encoded Mel Filterbank Energies for Environmental Sound Classification

Cited by 31 publications

References 13 publications

Construction of a Soundscape-Based Media Art Exhibition to Improve User Appreciation Experience by Using Deep Neural Networks

Construction of a Soundscape-Based Media Art Exhibition to Improve User Appreciation Experience by Using Deep Neural Networks

Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices

Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker Verification

Contact Info

Product

Resources

About