Evaluation of Gated Recurrent Neural Networks in Music Classification Tasks

Jakubik, Jan

doi:10.1007/978-3-319-67220-5_3

Cited by 10 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extracted features and segment representation of the initial frame were combined to obtain the fusional segment feature, which achieved an accuracy of 89.71% . Both GRU and LSTM were used to classify music and achieved 92% and 89% accuracy on the GTZAN dataset by Jukubik [28]. GRU and LSTM solve gradient vanishing and exploding problems of vanilla RNN, but they both are still susceptible to gradient decay as they both use sigmoid and hyperbolic tangent functions.…”

Section: Literature Reviewmentioning

confidence: 99%

“…A BN, ReLU activation, convolution, and average-pooling made the transition layer. In the final decision layer, global average pooling [28] took the average of each feature map to form a resulting vector and Copyright © 2021 MECS I.J. Information Technology and Computer Science, 2021, 2, 1-14 fed it to a softmax log-loss function, which produced a distribution over genre labels.…”

Section: Construction Of the Used Bbnnmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification

Rafi¹,

Mohammed²,

Prodhan³

et al. 2021

IJITCS

View full text Add to dashboard Cite

Among the many music information retrieval (MIR) tasks, music genre classification is noteworthy. The categorization of music into different groups that came to existence through a complex interplay of cultures, musicians, and various market forces to characterize similarities between compositions and organize collections is known as a music genre. The past researchers extracted various hand-crafted features and developed classifiers based on them. But the major drawback of this approach was the requirement of field expertise. However, in recent times researchers, because of the remarkable classification accuracy of deep learning models, have used similar models for MIR tasks. Convolutional Neural Net- work (CNN), Recurrent Neural Network (RNN), and the hybrid model, Convolutional - Recurrent Neural Network (CRNN), are such prominently used deep learning models for music genre classification along with other MIR tasks and various architectures of these models have achieved state-of-the-art results. In this study, we review and discuss three such architectures of deep learning models, already used for music genre classification of music tracks of length of 29-30 seconds. In particular, we analyze improved CNN, RNN, and CRNN architectures named Bottom-up Broadcast Neural Network (BBNN) [1], Independent Recurrent Neural Network (IndRNN) [2] and CRNN in Time and Frequency dimensions (CRNN- TF) [3] respectively, almost all of the architectures achieved the highest classification accuracy among the variants of their base deep learning model. Hence, this study holds a comparative analysis of the three most impressive architectural variants of the main deep learning models that are prominently used to classify music genre and presents the three architecture, hence the models (CNN, RNN, and CRNN) in one study. We also propose two ways that can improve the performances of the RNN (IndRNN) and CRNN (CRNN-TF) architectures.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Construction Of the Used Bbnnmentioning

confidence: 99%

Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification

Rafi¹,

Mohammed²,

Prodhan³

et al. 2021

IJITCS

View full text Add to dashboard Cite

show abstract

“…The output of CNN is pooled to a feature map of a smaller dimension as an input to RNN, keeping an aptitude to process sequential data by utilizing its memory unit. By this ability, it examines the long term dependency and important patterns hidden in sequential data explained in [36]. A Global Layer Regularization (GLR) is applied to the combined model that reduces the dimensions by computing statistics across each feature and helps in finding optimal parameters quickly for training.…”

Section: The Proposed Globally Regularized Cnn-rnn Architecturementioning

confidence: 99%

A Globally Regularized Joint Neural Architecture for Music Classification

et al. 2020

View full text Add to dashboard Cite

“…Classical songs correctly predicted with overall 87% of data and Sufi songs correctly predicted with overall 82% of data. Jan Jakubik [7], they performed with two Recurrent Neural Network (RNN): LSTM and GRU. They experiment on 4 datasets: GTZAN, Emotify, Ballroom and LastFM.…”

Section: Related Workmentioning

confidence: 99%

Music Genre Classification using Spectral Analysis Techniques With Hybrid Convolution-Recurrent Neural Network

Ahmad*¹,

Sahil²

2019

IJITEE

View full text Add to dashboard Cite

In this work, the objective is to classify the audio data into specific genres from GTZAN dataset which contain about 10 genres. First, it perform the audio splitting to make it signal into clips which contains homogeneous content. Short-term Fourier Transform (STFT), Mel-spectrogram and Mel-frequency cepstrum coefficient (MFCC) are the most common feature extraction technique and each feature extraction technique has been successful in their own various audio applications. Then, these feature extractions of the audio fed to the Convolution Neural Network (CNN) model and VGG16 Neural Network model, which consist of 16 convolution layers network. We perform different feature extraction with different CNN and VGG16 model with or without different Recurrent Neural Network (RNN) and evaluated performance measure. In this model, it has achieved overall accuracy 95.5\% for this task.

show abstract

Evaluation of Gated Recurrent Neural Networks in Music Classification Tasks

Cited by 10 publications

References 10 publications

Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification

Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification

A Globally Regularized Joint Neural Architecture for Music Classification

Music Genre Classification using Spectral Analysis Techniques With Hybrid Convolution-Recurrent Neural Network

Contact Info

Product

Resources

About