Bob L Sturm
Biographic Data
| ID | 1176600 |
|---|---|
| NAME | Bob L Sturm |
| GIVEN NAMES | Bob L |
| FAMILY NAME | Sturm |
| SIGNATURE | STURM B L |
| AFFILIATIONS | KTH Royal Institute of Technology |
| ORCID | 0000-0003-2549-6367 |
| VERIFIED | Yes |
| TOTAL WORKS | 7 |
| TOTAL CITATIONS | 6 |
| AUTHOR COUNT | 7 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2005 |
| LATEST PUBLICATION YEAR | 2024 |
| H-INDEX | 1 |
Innovation, data colonialism and ethics
By definition, traditional music is in a constant state of friction with innovation, exemplified by resistance to ‘outside’ influences such as different instruments, different ways of learning, and forces of commercialisation. An emerging external influence is artificial intelligence (AI), which is now capable of synthesising music collections at scales dwarfing those crafted by people and communities. In this paper, we examine the impact of rese…
How Music AI Is Useful
Critical but often overlooked research questions in artificial intelligence applied to music involve the impact of the results for music. How and to what extent does such research contribute to the domain of music? How are the resulting models useful for music practitioners? This article describes work arising from research engaging with composers, musicians and audiences to address such questions: two websites that make their AI models accessibl…
Machine learning research that matters for music creation
Research applying machine learning to music modelling and generation typically proposes model architectures, training methods and datasets, and gauges system performance using quantitative measures like sequence likelihoods and/or qualitative listening tests. Rarely does such work explicitly question and analyse its usefulness for and impact on real-world practitioners, and then build on those outcomes to inform the development and application of…
The State of the Art Ten Years After a State of the Art
A decade has passed since the first review of research on a ‘flagship application’ of music information retrieval (MIR): the problem of music genre recognition (MGR). During this time, about 500 works addressing MGR have been published, and at least 10 campaigns have been run to evaluate MGR systems. This makes MGR one of the most researched areas of MIR. So, where does MGR now lie? We show that in spite of this massive amount of work, MGR does n…
Analysis, Visualization, and Transformation of Audio Signals Using Dictionary-based Methods
In this article we provide an overview of dictionary-based methods (DBMs)—also called sparse approximation and atomic decomposition—and review our recent work on their application to working with data, specifically audio and music signals. As Fourier analysis is to additive synthesis, DBMs can be seen as the analytical counterparts to granular synthesis since they describe how a given signal can be built by a linear combination of heterogeneous a…
Concatenative sound synthesis and intellectual property
Concatenative sound synthesis (CSS) is only as good as the database from which it draws its sound units. As in concatenative speech synthesis, “good” sound concatenations require databases rich in sound material. How better to satisfy this than by using the world's entire library of sound recordings? As can be expected, this concatenative fodder includes work protected by copyrights; and some of these rights appear to forbid the use of these work…
Pulse of an Ocean
The author presents his work in sonifying ocean buoy data for scientific, pedagogical and compositional purposes. Mapping the spectral buoy data to audible frequencies creates interesting and illuminating sonifications of ocean wave dynamics. Several phenomena can be heard, including both those visible and those invisible in graphical representations of the data. The author has worked extensively with this data to compose music and to produce Mus…
The State of the Art Ten Years After a State of the Art
A decade has passed since the first review of research on a ‘flagship application’ of music information retrieval (MIR): the problem of music genre recognition (MGR). During this time, about 500 works addressing MGR have been published, and at least 10 campaigns have been run to evaluate MGR systems. This makes MGR one of the most researched areas of MIR. So, where does MGR now lie? We show that in spite of this massive amount of work, MGR does n…
How Music AI Is Useful
Critical but often overlooked research questions in artificial intelligence applied to music involve the impact of the results for music. How and to what extent does such research contribute to the domain of music? How are the resulting models useful for music practitioners? This article describes work arising from research engaging with composers, musicians and audiences to address such questions: two websites that make their AI models accessibl…
Machine learning research that matters for music creation
Research applying machine learning to music modelling and generation typically proposes model architectures, training methods and datasets, and gauges system performance using quantitative measures like sequence likelihoods and/or qualitative listening tests. Rarely does such work explicitly question and analyse its usefulness for and impact on real-world practitioners, and then build on those outcomes to inform the development and application of…
Concatenative sound synthesis and intellectual property
Concatenative sound synthesis (CSS) is only as good as the database from which it draws its sound units. As in concatenative speech synthesis, “good” sound concatenations require databases rich in sound material. How better to satisfy this than by using the world's entire library of sound recordings? As can be expected, this concatenative fodder includes work protected by copyrights; and some of these rights appear to forbid the use of these work…
Pulse of an Ocean
The author presents his work in sonifying ocean buoy data for scientific, pedagogical and compositional purposes. Mapping the spectral buoy data to audible frequencies creates interesting and illuminating sonifications of ocean wave dynamics. Several phenomena can be heard, including both those visible and those invisible in graphical representations of the data. The author has worked extensively with this data to compose music and to produce Mus…
Pulse of an Ocean
The author presents his work in sonifying ocean buoy data for scientific, pedagogical and compositional purposes. Mapping the spectral buoy data to audible frequencies creates interesting and illuminating sonifications of ocean wave dynamics. Several phenomena can be heard, including both those visible and those invisible in graphical representations of the data. The author has worked extensively with this data to compose music and to produce Mus…
Concatenative sound synthesis and intellectual property
Concatenative sound synthesis (CSS) is only as good as the database from which it draws its sound units. As in concatenative speech synthesis, “good” sound concatenations require databases rich in sound material. How better to satisfy this than by using the world's entire library of sound recordings? As can be expected, this concatenative fodder includes work protected by copyrights; and some of these rights appear to forbid the use of these work…
Analysis, Visualization, and Transformation of Audio Signals Using Dictionary-based Methods
In this article we provide an overview of dictionary-based methods (DBMs)—also called sparse approximation and atomic decomposition—and review our recent work on their application to working with data, specifically audio and music signals. As Fourier analysis is to additive synthesis, DBMs can be seen as the analytical counterparts to granular synthesis since they describe how a given signal can be built by a linear combination of heterogeneous a…
The State of the Art Ten Years After a State of the Art
A decade has passed since the first review of research on a ‘flagship application’ of music information retrieval (MIR): the problem of music genre recognition (MGR). During this time, about 500 works addressing MGR have been published, and at least 10 campaigns have been run to evaluate MGR systems. This makes MGR one of the most researched areas of MIR. So, where does MGR now lie? We show that in spite of this massive amount of work, MGR does n…
Machine learning research that matters for music creation
Research applying machine learning to music modelling and generation typically proposes model architectures, training methods and datasets, and gauges system performance using quantitative measures like sequence likelihoods and/or qualitative listening tests. Rarely does such work explicitly question and analyse its usefulness for and impact on real-world practitioners, and then build on those outcomes to inform the development and application of…
How Music AI Is Useful
Critical but often overlooked research questions in artificial intelligence applied to music involve the impact of the results for music. How and to what extent does such research contribute to the domain of music? How are the resulting models useful for music practitioners? This article describes work arising from research engaging with composers, musicians and audiences to address such questions: two websites that make their AI models accessibl…
Innovation, data colonialism and ethics
By definition, traditional music is in a constant state of friction with innovation, exemplified by resistance to ‘outside’ influences such as different instruments, different ways of learning, and forces of commercialisation. An emerging external influence is artificial intelligence (AI), which is now capable of synthesising music collections at scales dwarfing those crafted by people and communities. In this paper, we examine the impact of rese…
Computer Science (6 works) · Art (3 works) · Music and Audio Processing (3 works) · Music Technology and Sound Studies (3 works) · Visual arts (3 works) · Data science (2 works) · Diverse Musicological Studies (2 works) · Musical (2 works) · Neuroscience and Music Perception (2 works) · Philosophy (2 works)