Considerations for the Next Generation of Singing Tutor Systems

Faghih B, Timoney J. Considerations for the Next Generation of Singing Tutor Systems. In: AES Convention 146. Audio Engineering Society; 2019. Paper 506. Available from: https://aes.org/publications/elibrary-page/?id=20364

@inproceedings{Faghih2019_20364,
  author = {Faghih, Behnam and Timoney, Joseph},
  title = {{Considerations for the Next Generation of Singing Tutor Systems}},
  booktitle = {AES Convention 146},
  note = {Paper 506},
  year = {2019},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20364}
}

TY  - CPAPER
TI  - Considerations for the Next Generation of Singing Tutor Systems
AU  - Faghih, Behnam
AU  - Timoney, Joseph
T2  - AES Convention 146
M1  - Paper 506
PY  - 2019
DA  - 2019/03/06
UR  - https://aes.org/publications/elibrary-page/?id=20364
PB  - Audio Engineering Society
LA  - en
AB  - Recently software systems have been proposed to accelerate the progress of singing beginners. The basics of these systems are: the pitch of the sung notes is detected and algorithmic errors removed. Then, an alignment is made with a melodic ground truth, often as a midi representation, using techniques including Dynamic Time Warping and Hidden Markov Models. Although results have been reasonable, significant drawbacks to these alignment schemes include how a “musically acceptable” alignment can be identified, dynamic singer behavior, multiple repeated notes, and dealing with omitted or extra notes. To this end an improved singing analysis system structure is proposed that includes psychoacoustic models and intelligent decision making. Justification is given along with a description of a structured evaluation procedure.
ER  -