Estimation of elements related to musical concepts: Challenges
From MIReS
- Separate the various sources of an audio signal. The separation of the various sources of an audio track (source separation) facilitates its conversion to a symbolic representation (including the score and the instrument names). Conversely, the prior knowledge of this symbolic information (score and/or instruments) facilitates the separation of the sources. Despite the efforts made over the last decades, efficient source separation and multi-pitch estimation algorithms are still lacking. Alternative strategies should therefore be exploited in order to achieve both tasks, such as collaborative estimation.
- Jointly estimate the musical concepts. In a music piece, many of the different parameters are inter-dependent (notes often start on beat or tatum positions, pitch most likely belongs to the local key). Holistic/joint estimation should be considered to improve the performance of algorithms and the associated computational issues should be solved.
- Develop style-specific musical representations and estimation algorithms. Depending on the music style, different types of representation may be used (e.g. full score for classical music and lead sheets for jazz). Based on previous knowledge of the music style, a priori information may be used to help the estimation of the relevant musical concepts.
- Consider non-Western notation systems. Currently, most analyses are performed from the point of view of Western symbolic notation. Dependence of our algorithms on this system should be made explicit. Other notation systems, other informative and user-adapted music representations, possibly belonging to other music cultures, should be considered, and taken into account by our algorithms.
- Compute values for the reliability of musical concept estimation. Many musical concepts (such as multi-pitch or tempo) are obtained through "estimation" (as opposed to MFCC which is a cascade of mathematical operators). Therefore the values obtained by these estimations may be wrong. The challenge is to enable algorithms to compute a measure of the reliability of their estimation ("how much the algorithm is sure about its estimation"). From a research point of view, this will allow the use of this "uncertainty" estimation in a higher-level system. From an exploitation point of view, this will allow the use of these estimations for automatically tagging music without human intervention.
- Take into account reliability in systems. Estimations of musical concepts (such as multi-pitch or beat) can be used to derive higher-level musical analysis. We should study how the uncertainty of the estimation of these musical concepts can be taken into account in higher-level algorithms.
- Develop user-assisted systems. If it is not possible to estimate the musical concepts fully automatically, then a challenge is to study how this can been done interactively with the user (using relevance feedback).
