Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Emotion and Adaptation

Emotion and Meaning in Music

This paper surveys the state of the art in automatic emotion recognition in music. Music is oftentimes referred to as a “language of emotion” [1], and it is natural for us to categorize music in terms of its emotional associations. Myriad features, such as harmony, timbre, interpretation, and lyrics affect emotion, and the mood of a piece may also change over its duration. But in developing automated systems to organize music in terms of emotional content, we are faced with a problem that oftentimes lacks a welldefined answer; there may be considerable disagreement regarding the perception and interpretation of the emotions of a song or ambiguity within the piece itself. When compared to other music information retrieval tasks (e.g., genre identification), the identification of musical mood is still in its early stages, though it has received increasing attention in recent years. In this paper we explore a wide range of research in music emotion recognition, particularly focusing on methods that use contextual text information (e.g., websites, tags, and lyrics) and content-based approaches, as well as systems combining multiple feature domains.

https://ismir2010.ismir.net/proceedings/ismir2010-45.pdf

Music emotion recognition: A state of the art review

Music information retrieval (MIR) is an emerging research area that receives growing attention from both the research community and music industry. It addresses the problem of querying and retrieving certain types of music from large music data set. Classification is a fundamental problem in MIR. Many tasks in MIR can be naturally cast in a classification setting, such as genre classification, mood classification, artist recognition, instrument recognition, etc. Music annotation, a new research area in MIR that has attracted much attention in recent years, is also a classification problem in the general sense. Due to the importance of music classification in MIR research, rapid development of new methods, and lack of review papers on recent progress of the field, we provide a comprehensive review on audio-based classification in this paper and systematically summarize the state-of-the-art techniques for music classification. Specifically, we have stressed the difference in the features and the types of classifiers used for different classification tasks. This survey emphasizes on recent development of the techniques and discusses several open issues for future research.

A Survey of Audio-Based Music Classification and Annotation

In this paper we present a study on music mood classification using audio and lyrics information. The mood of a song is expressed by means of musical features but a relevant part also seems to be conveyed by the lyrics. We evaluate each factor independently and explore the possibility to combine both, using natural language processing and music information retrieval techniques. We show that standard distance-based methods and latent semantic analysis are able to classify the lyrics significantly better than random, but the performance is still quite inferior to that of audio-based techniques. We then introduce a method based on differences between language models that gives performances closer to audio-based classifiers. Moreover, integrating this in a multimodal system (audio+text) allows an improvement in the overall performance. We demonstrate that lyrics and audio information are complementary, and can be combined to improve a classification system.

/pdf/multimodal-music-mood-classification-using-audio-and-lyrics-17ux04ifaq.pdf

Multimodal Music Mood Classification Using Audio and Lyrics

Recent music information retrieval (MIR) research pays increasing attention to music classification based on moods expressed by music pieces The first Audio Mood Classification (AMC) evaluation task was held in the 2007 running of the Music Information Retrieval Evaluation eXchange (MIREX) This paper describes important issues in setting up the task, including dataset construction and ground-truth labeling, and analyzes human assessments on the audio dataset, as well as system performances from various angles Interesting findings include system performance differences with regard to mood clusters and the levels of agreement amongst human judgments regarding mood labeling Based on these analyses, we summarize experiences learned from the first community scale evaluation of the AMC task and propose recommendations for future AMC and similar evaluation tasks

/pdf/the-2007-mirex-audio-mood-classification-task-lessons-46f9aghmox.pdf

The 2007 MIREX Audio Mood Classification Task: Lessons Learned

This paper presents ndings about mood representations.We aim to analyze how do people tag music by mood, tocreate representations based on this data and to study theagreement between experts and a large community. Forthispurpose,wecreateasemanticmoodspacefromlast.fmtags using Latent Semantic Analysis. With an unsuper-vised clustering approach, we derive from this space anideal categorical representation. We compare our commu-nitybasedsemanticspacewithexpertrepresentationsfromHevner and the clusters from the MIREX Audio MoodClassication task. Using dimensional reduction with aSelf-Organizing Map, we obtain a 2D representation thatwe compare with the dimensional model from Russell. Wepresent as well a tree diagram of the mood tags obtainedwith a hierarchical clustering approach. All these resultsshow a consistency between the community and the ex-perts as well as some limitations of current expert models.This study demonstrates a particular relevancy of the basicemotions model with four mood clusters that can be sum-marized as: happy, sad, angry and tender. This outcomecan help to create better ground truth and to provide morerealistic mood classication algorithms. Furthermore, thismethod can be applied to other types of representations tobuild better computational models.1. INTRODUCTIONMusicclassicationbymood

/pdf/music-mood-representations-from-social-tags-2dfmyzdvny.pdf

Music mood representations from social tags

Music perception is highly intertwined with both emotions and context. Not surprisingly, many of the users’ information seeking actions aim at retrieving music songs based on these perceptual dimensions ‐ moods and themes, expressing how people feel about music or which situations they associate it with. In order to successfully support music retrieval along these dimensions, powerful methods are needed. Still, most existing approaches aiming at inferring some of the songs’ latent characteristics focus on identifying musical genres. In this paper we aim at bridging this gap between users’ information needs and indexed music features by developing algorithms for classifying music songs by moods and themes. We extend existing approaches by also considering the songs’ thematic dimensions and by using social data from the Last.fm music portal, as support for the classification tasks. Our methods exploit both audio features and collaborative user annotations, fusing them to improve overall performance. Evaluation performed against the AllMusic.com ground truth shows that both kinds of information are complementary and should be merged for enhanced classification accuracy.

/pdf/music-mood-and-theme-classification-a-hybrid-approach-45q6ld7ryr.pdf

Music mood and theme classification - a hybrid approach

In this paper we present a way to annotate music collections by exploiting audio similarity. Similarity is used to propose labels (tags) to yet unlabeled songs, based on the content‐based distance between them. The main goal of our work is to ease the process of annotating huge music collections, by using content-based similarity distances as a way to propagate labels among songs. We present two different experiments. The first one propagateslabelsthatarerelatedwiththestyleofthepiece, whereas the second experiment deals with mood labels. On the one hand, our approach shows that using a music collection annotated at 40% with styles, the collection can be automatically annotated up to 78% (that is, 40% already annotated and the rest, 38%, only using propagation), with a recall greater than 0.4. On the other hand, for a smaller music collection annotated at 30% with moods, the collection can be automatically annotated up to 65% (e.g. 30% plus 35% using propagation).

/pdf/annotating-music-collections-how-content-based-similarity-4vflpmmptc.pdf

C. Laurier

Papers

Multimodal Music Mood Classification Using Audio and Lyrics

The 2007 MIREX Audio Mood Classification Task: Lessons Learned

Music mood representations from social tags

Music mood and theme classification - a hybrid approach

Annotating music collections: how content-based similarity helps to propagate labels