Music emotion analysis using semantic embedding recurrent neural networks

Jakubik, Jan; Kwaśnicka, Halina

doi:10.1109/inista.2017.8001169

Cited by 11 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some reduce the length of music piece to reduce the time taken for database analysis process. Thayers [17], [61], [62], [48], [63], [19], [64], [65] Categorical [66] Russel's [18], [40], [67] 2-d [34] GEMS [68] Indian classical model [19] Hevner [64] Authors may also provide the list of adjective terms and their synonyms to categorize the songs to reduce the time consumption. Some example songs with defined categories may also be provided to the group for better judgment of the class belonging to particular song.…”

Section: B Dimensional Approachmentioning

confidence: 99%

A Survey on Autonomous Techniques for Music Classification based on Human Emotions Recognition

Chaudhary¹,

Singh²,

Singh³

2020

IJCDS

View full text Add to dashboard Cite

Music is one of the finest element to trigger emotions in human beings. Each and every human being feels the music and emotions are automatically provoked by listening music. Music is considered as strong stress reliever. With the increase in size of music dataset available online and advancement of automation technologies the emotions from the music are to be recognized automatically so that the online database of music can be organized and browsed in an efficient manner. Automation of music emotion classification (MEC) helps the people to listen the music of their interest without wasting time on surfing the internet. It helps the psychologists in treatment process of patients. It also helps the musicians and artists to work on specific type of music and to classify them. This paper aims to provide the overview and survey related to autonomous technique for music classification (ATMC). In this article, the basic steps such as database collection, preprocessing, database analysis, feature extraction, classification and evaluation parameters involved in ATMC are explained and comprehensive review related to the basic steps is summarized. Research issues and solutions related to ATMC along with future scope are also discussed in this article.

show abstract

Section: B Dimensional Approachmentioning

confidence: 99%

A Survey on Autonomous Techniques for Music Classification based on Human Emotions Recognition

Chaudhary¹,

Singh²,

Singh³

2020

IJCDS

View full text Add to dashboard Cite

show abstract

“…For batch learning, which is currently the standard procedure for learning neural networks due to performance considerations, the matrices K F, F and K A, A can be calculated over batches instead of full dataset. We described this approach in less general terms in [19] as semantic embedding, borrowing the idea from the domain of text processing [26]. Semantic embedding in texts seeks to learn similarity between documents using pairs of similar and dissimilar files and could be considered a special case of the described idea (with cosine similarity as the k function and K A, A being built as a matrix of ones and zeroes from known relation of similarity, rather than calculated from annotations).…”

Section: Similarity-based Loss For a Neural Networkmentioning

confidence: 99%

“…(i) Cosine: the similarity notion that we used in the earlier paper [19], where we first tackled learning similarity. It was previously used in the approach to learning similarity between documents called semantic embedding.…”

Section: Measures Of Similarity Between Vectorsmentioning

confidence: 99%

“…We chose both datasets that were previously tested in [19] and three complementary datasets. Complementary data represents an important form of emotion regression (predicting the values of valence and arousal) and two music classification tasks not concerning emotion.…”

Section: Datasetsmentioning

confidence: 99%

“…While deep learning in itself performs very well, it creates new opportunities for the use of older machine learning methods. The features can be taken from the selected level of deep network and used as an input to a support vector machine (SVM), or a regression method such as SVR, or any other classifier [19].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Similarity‐Based Summarization of Music Files for Support Vector Machines

Jakubik

Kwaśnicka

2018

Complexity

Self Cite

View full text Add to dashboard Cite

Automatic retrieval of music information is an active area of research in which problems such as automatically assigning genres or descriptors of emotional content to music emerge. Recent advancements in the area rely on the use of deep learning, which allows researchers to operate on a low-level description of the music. Deep neural network architectures can learn to build feature representations that summarize music files from data itself, rather than expert knowledge. In this paper, a novel approach to applying feature learning in combination with support vector machines to musical data is presented. A spectrogram of the music file, which is too complex to be processed by SVM, is first reduced to a compact representation by a recurrent neural network. An adjustment to loss function of the network is proposed so that the network learns to build a representation space that replicates a certain notion of similarity between annotations, rather than to explicitly make predictions. We evaluate the approach on five datasets, focusing on emotion recognition and complementing it with genre classification. In experiments, the proposed loss function adjustment is shown to improve results in classification and regression tasks, but only when the learned similarity notion corresponds to a kernel function employed within the SVM. These results suggest that adjusting deep learning methods to build data representations that target a specific classifier or regressor can open up new perspectives for the use of standard machine learning methods in music domain.

show abstract

Binary Emotion Classification of Music Using Deep Neural Networks

Revathy

Pillai

2022

Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021)

View full text Add to dashboard Cite

Music emotion analysis using semantic embedding recurrent neural networks

Cited by 11 publications

References 13 publications

A Survey on Autonomous Techniques for Music Classification based on Human Emotions Recognition

A Survey on Autonomous Techniques for Music Classification based on Human Emotions Recognition

Similarity‐Based Summarization of Music Files for Support Vector Machines

Binary Emotion Classification of Music Using Deep Neural Networks

Contact Info

Product

Resources

About