Music informatics is an interdisciplinary research area that encompasses data driven approaches to the analysis, generation, and retrieval of music. In the era of big data, two goals weigh heavily on many research agendas in this area: (a) the identification of better features and (b) the acquisition of better training data. To this end, researchers have started to incorporate findings and methods from music cognition, a related but historically distinct research area that is concerned with elucidating the underlying mental processes involved in music-related behavior.
Researchers in music cognition have started to embrace signal-based features to complement music-theoretic features, and machine-learning methods to complement traditional inferential statistics. These new directions have allowed researchers to study music-related behavior in an ecologically valid manner involving multiple variables and naturally occurring nonlinear relationships.
In sum, there are numerous indications of a growing interest in bridging aspects of music informatics with music cognition. Formal “bridging sessions” have been held at major meetings and at specialized symposia. The published literature has also witnessed an uptick in the number of studies that have investigated music from both perspectives.
Similar trends have begun to surface in the applied domain. Music recommender systems are increasingly incorporating listener data as well as listener feedback to support advanced customization. Music generation technology has embraced a diverse array of input modalities and metrics leading to new methods by which users may compose and record music.
This Frontiers Research Topic will provide a forum to highlight new research that integrates approaches derived from music informatics and music cognition. We welcome authors to contribute new studies or review articles. Potential topics include, but are not limited to the following:
- Computational modeling of music similarity
- Computational modeling of music emotion
- Cognitively based approaches to music information retrieval
- Cognitively based approaches to music analysis
Music informatics is an interdisciplinary research area that encompasses data driven approaches to the analysis, generation, and retrieval of music. In the era of big data, two goals weigh heavily on many research agendas in this area: (a) the identification of better features and (b) the acquisition of better training data. To this end, researchers have started to incorporate findings and methods from music cognition, a related but historically distinct research area that is concerned with elucidating the underlying mental processes involved in music-related behavior.
Researchers in music cognition have started to embrace signal-based features to complement music-theoretic features, and machine-learning methods to complement traditional inferential statistics. These new directions have allowed researchers to study music-related behavior in an ecologically valid manner involving multiple variables and naturally occurring nonlinear relationships.
In sum, there are numerous indications of a growing interest in bridging aspects of music informatics with music cognition. Formal “bridging sessions” have been held at major meetings and at specialized symposia. The published literature has also witnessed an uptick in the number of studies that have investigated music from both perspectives.
Similar trends have begun to surface in the applied domain. Music recommender systems are increasingly incorporating listener data as well as listener feedback to support advanced customization. Music generation technology has embraced a diverse array of input modalities and metrics leading to new methods by which users may compose and record music.
This Frontiers Research Topic will provide a forum to highlight new research that integrates approaches derived from music informatics and music cognition. We welcome authors to contribute new studies or review articles. Potential topics include, but are not limited to the following:
- Computational modeling of music similarity
- Computational modeling of music emotion
- Cognitively based approaches to music information retrieval
- Cognitively based approaches to music analysis
