Our research in MIR is driven by two guiding principles:
1. The next generation of music technologies will be based on machine understanding of music, helping us to find music we like from a sea of content and create music with more intuitive and powerful tools. More people will be able to engage with and create music, experiencing and sharing its emotional benefits, and there will be new modes of expression for performers and composers.
2. Computational modeling of music will help us to understand human creativity and lead to new creative partnerships between musicians as well as between musicians and computers. I am particularly interested in musical improvisation.
Our music cognition is driven by the beliefs that:
1. By understanding our complex multi-layered response to music, we will begin to see the connection between abstract sound patterns and the profoundly moving experiences that music can engender.
2. Because music involves so many aspects of cognition, from complex auditory pattern recognition, to attention, memory and emotion, its understanding will provide a window into the mind.
MIR and music cognition are complementary perspectives in researching the fundamental mystery of music. By combining a close analysis of musical sound and structure with the knowledge of how the brain processes music, we will begin to understand how our experience of music is created. This will enable more musically intelligent systems to be built.
Research Projects
Current
-
The goal of this NSF CAREER project is to develop machine- learning (ML) models for predicting temporally structured events in the context of music, which take advantage of these complex correlations, and to use these models to help explain human musical expectation.
-
The objectives are to develop computational models of improvisation and to use them to develop new technologies that support creativity in music and education.
-
Just as key recognition is essential for understanding Western tonal music (including pop, rock, jazz, etc) -- because it is fundamental to understanding the melodic and harmonic content of a piece -- raag understanding is essential for systems that interact with Indian music.
-
Tabla and Mrdangam are the main percussion instruments of North and South India respectively. Both traditions are highly virtuosic and are organized around timbre. "melodies" are created from timbres as opposed to pithces and organized in a highly structured way. The system is analaogus to language in that small units are combined hierarchically to form larger expressions
-
One of the most active areas of MIR research is content-based recommendation, analyzing the semantic content of songs to judge their relatedness. This information is used to make recommendations of the form: "if you like A, you'll also like B".
-
I am interested in constructing a cognitively grounded theory of raag, the fundamental melodic concept of Indian music, that explains how raags evoke emotions.
-
We have been examining whether certain emotional responses to raag music can be traced to pitch statistics such as frequency of usage and conditional frequency of usage (i.e. how often one note follows another). We have also begun examining the role that micro-pitch structure such as pitch glides and ornaments play in evoking emotion.
-
--with Vinod Menon [Stanford], David Huron [OSU], and Daniel Abrams [Stanford]
In this work we are exploring amygdala activation in response to simple stimuli such as rising and falling intensity and rising and falling pitch tones.
