A Globally Regularized Joint Neural Architecture for Music Classification

Ashraf, Mohsin; Geng, Guohua; Ahmad, Farooq; Abid, Fazeel

doi:10.1109/access.2020.3043142

Cited by 26 publications

(12 citation statements)

References 41 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result of this comparison advocates the effective use of OELM in the field of software maintenance-based projects. The use of AI in different fields is evident [27][28][29][30].…”

Section: Literature Reviewmentioning

confidence: 99%

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

Ikram¹,

Jalil²,

Ngah³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Software maintenance is the process of fixing, modifying, and improving software deliverables after they are delivered to the client. Clients can benefit from offshore software maintenance outsourcing (OSMO) in different ways, including time savings, cost savings, and improving the software quality and value. One of the hardest challenges for the OSMO vendor is to choose a suitable project among several clients' projects. The goal of the current study is to recommend a machine learning-based decision support system that OSMO vendors can utilize to forecast or assess the project of OSMO clients. The projects belong to OSMO vendors, having offices in developing countries while providing services to developed countries. In the current study, Extreme Learning Machine's (ELM's) variant called Deep Extreme Learning Machines (DELMs) is used. A novel dataset consisting of 195 projects data is proposed to train the model and to evaluate the overall efficiency of the proposed model. The proposed DELM's based model evaluations achieved 90.017% training accuracy having a value with 1.412 × 10 -3 Root Mean Square Error (RMSE) and 85.772% testing accuracy with 1.569 × 10 −3 RMSE with five DELMs hidden layers. The results express that the suggested model has gained a notable recognition rate in comparison to any previous studies. The current study also concludes DELMs as the most applicable and useful technique for OSMO client's project assessment.

show abstract

“…The result of this comparison advocates the effective use of OELM in the field of software maintenance-based projects. The use of AI in different fields is evident [27][28][29][30].…”

Section: Literature Reviewmentioning

confidence: 99%

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

Ikram¹,

Jalil²,

Ngah³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…As shown in The SOTA methods GTZAN dataset (%) Bisharad et al [7] 85.36 Bisharad et al [8] 82.00 Raissi et al [42] 91.00 Sugianto et al [45] 71.87 Ashraf et al [3] 87.79 Ng et al [39] (FusionNet) 96.50 Liu et al [30] 93.90 Nanni et al [37] 90.60 Ours (MS-SincResNet) 91.49…”

Section: Ablation Studymentioning

confidence: 99%

MS-SincResNet: Joint Learning of 1D and 2D Kernels Using Multi-scale SincNet and ResNet for Music Genre Classification

Chang

Chen

Lee

2021

Proceedings of the 2021 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

In this study, we proposed a new end-to-end convolutional neural network, called MS-SincResNet, for music genre classification. MS-SincResNet appends 1D multi-scale SincNet (MS-SincNet) to 2D ResNet as the first convolutional layer in an attempt to jointly learn 1D kernels and 2D kernels during the training stage. First, an input music signal is divided into a number of fixed-duration (3 seconds in this study) music clips, and the raw waveform of each music clip is fed into 1D MS-SincNet filter learning module to obtain three-channel 2D representations. The learned representations carry rich timbral, harmonic, and percussive characteristics comparing with spectrograms, harmonic spectrograms, percussive spectrograms and Mel-spectrograms. ResNet is then used to extract discriminative embeddings from these 2D representations. The spatial pyramid pooling (SPP) module is further used to enhance the feature discriminability, in terms of both time and frequency aspects, to obtain the classification label of each music clip. Finally, the voting strategy is applied to summarize the classification results from all 3-second music clips. In our experimental results, we demonstrate that the proposed MS-SincResNet outperforms the baseline SincNet and many well-known hand-crafted features. Considering individual 2D representation, MS-SincResNet also yields competitive results with the state-of-the-art methods on the GTZAN dataset and the ISMIR2004 dataset. The code is

show abstract

“…CNN (convolutional neural networks) [11] and DNN (Deep Neural Networks) [12] are effective methods for device source identification, extracting the spatial correlation of related feature domains. LSTM (Long Short-Term Memory) can reasonably handle the temporal correlation in sequential data [13], which has certain advantages in the sequence model with long-term memory. In addition, the deep learning methods directly make predictions based on the input data, which are conducive to the design of an end-to-end framework for device source identification tasks [14].…”

Section: Introductionmentioning

confidence: 99%

“…Inspired by the success of deep learning for feature representation [12] and RNN for music classification tasks [13], we propose a device source identification method based on the end-to-end framework for the fusion of spatial and temporal features. In this proposed method, first, to fully explore the spatial information and temporal information of device source, spatial and temporal feature extraction networks are built to extract spatial and temporal information from GSV feature and MFCC feature.…”

Section: Introductionmentioning

confidence: 99%

Spatial and temporal learning representation for end-to-end recording device identification

Zeng

Zhu

Wang

et al. 2021

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Deep learning techniques have achieved specific results in recording device source identification. The recording device source features include spatial information and certain temporal information. However, most recording device source identification methods based on deep learning only use spatial representation learning from recording device source features, which cannot make full use of recording device source information. Therefore, in this paper, to fully explore the spatial information and temporal information of recording device source, we propose a new method for recording device source identification based on the fusion of spatial feature information and temporal feature information by using an end-to-end framework. From a feature perspective, we designed two kinds of networks to extract recording device source spatial and temporal information. Afterward, we use the attention mechanism to adaptively assign the weight of spatial information and temporal information to obtain fusion features. From a model perspective, our model uses an end-to-end framework to learn the deep representation from spatial feature and temporal feature and train using deep and shallow loss to joint optimize our network. This method is compared with our previous work and baseline system. The results show that the proposed method is better than our previous work and baseline system under general conditions.

show abstract

A Globally Regularized Joint Neural Architecture for Music Classification

Cited by 26 publications

References 41 publications

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

Project Assessment in Offshore Software Maintenance Outsourcing Using Deep Extreme Learning Machines

MS-SincResNet: Joint Learning of 1D and 2D Kernels Using Multi-scale SincNet and ResNet for Music Genre Classification

Spatial and temporal learning representation for end-to-end recording device identification

Contact Info

Product

Resources

About