1000 songs for emotional analysis of music

Soleymani, Mohammad; Micheal, N.; Schmidt, Evanthia Kalpazidou; Sha, Cheng-Ya; Yang, Yi-Hsuan

doi:10.1145/2506364.2506365

Cited by 132 publications

(76 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…MediaEval 2013 data, also known as "1000 songs" dataset [29], is a set created for machine learning benchmarking. It consists of 744 (after duplicate removal) unique song excerpts.…”

Section: Complexitymentioning

confidence: 99%

Similarity-Based Summarization of Music Files for Support Vector Machines

Jakubik

Kwaśnicka

2018

Complexity

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

“…MediaEval 2013 data, also known as "1000 songs" dataset [29], is a set created for machine learning benchmarking. It consists of 744 (after duplicate removal) unique song excerpts.…”

Section: Complexitymentioning

confidence: 99%

Similarity-Based Summarization of Music Files for Support Vector Machines

Jakubik

Kwaśnicka

2018

Complexity

View full text Add to dashboard Cite

show abstract

“…This module implements a method for allowing identification and extraction of arousal, valence pairs from a musical track. The emotion recognition capabilities have been implemented through Support Vector Machines (SVMs), trained with the dataset described in [18]. It includes approximately 1000 CC-licensed songs that have been listened and subsequently annotated with their values of arousal and valence through crowdsourcing.…”

Section: Use Casementioning

confidence: 99%

“…It includes approximately 1000 CC-licensed songs that have been listened and subsequently annotated with their values of arousal and valence through crowdsourcing. The training process uses 34 musical features extracted from each audio track of the aforementioned dataset, which constitute the training set inputs (see [18] for more details). Obviously, the corresponding arousal and valence annotations are used as outputs.…”

Section: Use Casementioning

confidence: 99%

Conveying Audience Emotions Through Humanoid Robot Gestures to an Orchestra During a Live Musical Exhibition

Giardina

Tramonte

Gentile

et al. 2017

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Abstract. In the last twenty years, robotics have been applied in many heterogeneous contexts. Among them, the use of humanoid robots during musical concerts have been proposed and investigated by many authors. In this paper, we propose a contribution in the area of robotics application in music, consisting of a system for conveying audience emotions during a live musical exhibition, by means of a humanoid robot. In particular, we provide all spectators with a mobile app, by means of which they can select a specific color while listening to a piece of music (act). Each color is mapped to an emotion, and the audience preferences are then processed in order to select the next act to be played. This decision, based on the overall emotion felt by the audience, is then communicated by the robot through body gestures to the orchestra. Our first results show that spectators enjoy such kind of interactive musical performance, and are encouraging for further investigations.

show abstract

“…The experiment was designed with a fixed duration of six minutes and 45 seconds. Six songs of 45 seconds were selected from a free music database [11] characterized by the emotional reaction. This duration was elected for an average speed of 35 km/h and an adequate duration of the test without an effect of fatigue that could affect the results.…”

Section: Ictte 2017mentioning

confidence: 99%

Music Recommendation System for Human Attention Modulation by Facial Recognition on a driving task: A Proof of Concept

et al. 2017

View full text Add to dashboard Cite

Abstract. The role of music on driving process had been discussed in the context of driver assistance as an element of security and comfort. Throughout this document, we present the development of an audio recommender system for the use by drivers, based on facial expression analysis. This recommendation system has the objective of increasing the attention of the driver by the election of specific music pieces. For this pilot study, we start presenting an introduction to audio recommender systems and a brief explanation of the function of our facial expression analysis system. During the driving course the subjects (seven participants between 19 and 25 years old) are stimulated with a chosen group of audio compositions and their facial expressions are captured via a camera mounted in the car's dashboard. Once the videos were captured and recollected, we proceeded to analyse them using the FACET™ module of the biometric capture platform iMotions™. This software provides us with the expression analysis of the subjects. Analysed data is postprocessed and the data obtained were modelled on a quadratic surface that was optimized based on the known cestrum and tempo of the songs and the average evidence of emotion. The results showed very different optimal points for each subject, that indicates different type of music for optimizing driving attention. This work is a first step for obtaining a music recommendation system capable to modulate subject attention while driving.

show abstract

1000 songs for emotional analysis of music

Cited by 132 publications

References 16 publications

Similarity-Based Summarization of Music Files for Support Vector Machines

Similarity-Based Summarization of Music Files for Support Vector Machines

Conveying Audience Emotions Through Humanoid Robot Gestures to an Orchestra During a Live Musical Exhibition

Music Recommendation System for Human Attention Modulation by Facial Recognition on a driving task: A Proof of Concept

Contact Info

Product

Resources

About