CNN based music emotion classification

Liu, Xin; Chen, Qingcai; Wu, Xiangping; Liu, Yan; Liu, Yang

doi:10.48550/arxiv.1704.05665

Cited by 4 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [99], a CNN is developed for emotion classification with 18 emotion tags, using time and frequency domain information. The experiments make use of the CAL500 (Turnbull 2007 forward) and CAL500exp ( [100]) datasets.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

et al. 2023

View full text Add to dashboard Cite

The discipline of Deep Learning has been recognized for its strong computational tools, which have been extensively used in data and signal processing, with innumerable promising results. Among the many commercial applications of Deep Learning, Music Signal Processing has received an increasing amount of attention over the last decade. This work reviews the most recent developments in Deep Learning in Music signal processing. Two main applications that are discussed are Music Information Retrieval, which spans a plethora of applications, and Music Generation, which can fit a range of musical styles. After a review of both topics, several emerging directions are identified for future research.

show abstract

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Different weights are allocated on different time blocks (chunks), and the song-level emotion classification prediction is obtained through fusion. Liu et al [22] regards music emotion recognition as a multi-label classification task, and uses convolutional neural networks and spectrum diagram to complete end-to-end classification. Chen et al [2] considered the complementarity between CNN with different structures and between CNN and LSTM, and combined multi-channel CNN with different structures and LSTM into a unified structure (Multi-channel Convolutional LSTM, MCCLSTM) to extract advanced music descriptors.…”

Section: Mer With Acoustic-onlymentioning

confidence: 99%

Beijing Qihoo Technology Co., Ltd. v. Tencent Technology (Shenzhen) Co., Ltd. and Shenzhen Tencent Computer System Co., Ltd. (Dispute over the Abuse of Market Dominant Position)—Analysis Methods and Ideas for the Definition of the Relevant Markets and the Abuse of Market Dominant Position in the Internet Environment

Zhu

2019

Library of Selected Cases From the Chinese Court

View full text Add to dashboard Cite

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting, attacker can fool the model without knowing model's parameters and architecture. Previous works on word-level attacks widely use single semantic space and greedy search as a search strategy. However, these methods fail to balance the attack success rate, quality of adversarial examples and time consumption. In this paper, we propose BeamAttack, a textual attack algorithm that makes use of mixed semantic spaces and improved beam search to craft high-quality adversarial examples. Extensive experiments demonstrate that BeamAttack can improve attack success rate while saving numerous queries and time, e.g., improving at most 7% attack success rate than greedy search when attacking the examples from MR dataset. Compared with heuristic search, BeamAttack can save at most 85% model queries and achieve a competitive attack success rate. The adversarial examples crafted by BeamAttack are highly transferable and can effectively improve model's robustness during adversarial training. Code is available at https://github.com/zhuhai-ustc/beamattack/tree/master

show abstract

“…By converting the original data into a spectral graph, and then inputting the spectral graph into the CNN for emotion recognition. Liu and others [6] use the spectral graph computed by the short-time Fourier transform of the audio signal as input. Each music's spectral graph undergoes convolutional layers, pooling layers, and hidden layers, and finally, it goes through SoftMax for prediction.…”

Section: Introductionmentioning

confidence: 99%

Violin Music Emotion Recognition with Fusion of CNN–BiGRU and Attention Mechanism

Ma,

Zhou

2024

Information

View full text Add to dashboard Cite

Music emotion recognition has garnered significant interest in recent years, as the emotions expressed through music can profoundly enhance our understanding of its deeper meanings. The violin, with its distinctive emotional expressiveness, has become a focal point in this field of research. To address the scarcity of specialized data, we developed a dataset specifically for violin music emotion recognition named VioMusic. This dataset offers a precise and comprehensive platform for the analysis of emotional expressions in violin music, featuring specialized samples and evaluations. Moreover, we implemented the CNN–BiGRU–Attention (CBA) model to establish a baseline system for music emotion recognition. Our experimental findings show that the CBA model effectively captures the emotional nuances in violin music, achieving mean absolute errors (MAE) of 0.124 and 0.129. The VioMusic dataset proves to be highly practical for advancing the study of emotion recognition in violin music, providing valuable insights and a robust framework for future research.

show abstract

CNN based music emotion classification

Cited by 4 publications

References 8 publications

Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

Violin Music Emotion Recognition with Fusion of CNN–BiGRU and Attention Mechanism

Contact Info

Product

Resources

About