Objective Descriptors for the Assessment of Student Music Performances

Vidwans A, Gururani S, Wu CW, Subramanian V, Swaminathan RV, Lerch A. Objective Descriptors for the Assessment of Student Music Performances. In: AES Conference: 2017 AES International Conference on Semantic Audio. Audio Engineering Society; 2017. Paper 3-3. Available from: https://aes.org/publications/elibrary-page/?id=18758

@inproceedings{Vidwans2017_18758,
  author = {Vidwans, Amruta and Gururani, Siddharth and Wu, Chih-Wei and Subramanian, Vinod and Swaminathan, Rupak Vignesh and Lerch, Alexander},
  title = {{Objective Descriptors for the Assessment of Student Music Performances}},
  booktitle = {AES Conference: 2017 AES International Conference on Semantic Audio},
  note = {Paper 3-3},
  year = {2017},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=18758}
}

TY  - CPAPER
TI  - Objective Descriptors for the Assessment of Student Music Performances
AU  - Vidwans, Amruta
AU  - Gururani, Siddharth
AU  - Wu, Chih-Wei
AU  - Subramanian, Vinod
AU  - Swaminathan, Rupak Vignesh
AU  - Lerch, Alexander
T2  - AES Conference: 2017 AES International Conference on Semantic Audio
M1  - Paper 3-3
PY  - 2017
DA  - 2017/06/06
UR  - https://aes.org/publications/elibrary-page/?id=18758
PB  - Audio Engineering Society
LA  - en
AB  - Assessment of students' music performances is a subjective task that requires the judgment of technical correctness as well as aesthetic properties. A computational model that automatically evaluates music performance based on objective measurements is often desirable to ensure the consistency and reproducibility of these assessments, e.g., for automatic music tutoring systems. In this study, we investigate the effectiveness of various audio descriptors for assessing students’ performances. Specifically, three different sets of features, including a baseline set, score-independent features, and score-based features, are compared with respect to their efficiency in regression tasks. The results show human assessments can be modeled to a certain degree, however, the generality of the model still needs further investigation.
ER  -