Sanna Wager
PhD Candidate, Music Informatics
Indiana University Bloomington
School of Informatics and Computing
scwager -(at)-


Deep autotuner

Sanna Wager, George Tzanetakis, Cheng-i Wang, and Minje Kim. “Deep Autotuner: A Pitch Correcting Network for Singing Performance,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020.

Paper and audio examples

News release by Indiana University SICE

Acoustic modeling

Sanna Wager, Aparna Khare, Minhua Wu, and Shiva Sundaram. “Fully learnable front- end for multi-channel acoustic modeling using semi-supervised learning,” in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020.

"Intonation" Dataset

S. Wager, G. Tzanetakis, S. Sullivan, C. Wang, J. Shimmin, M. Kim, and P. Cook, "Intonation: a dataset of quality vocal performances refined by spectral clustering on pitch congruence," Accepted for publication at IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), 2019.

Paper and link to dataset

Collaborative dereverberation

S. Wager and M. Kim, "Collaborative speech dereverberation: regularized tensor factorization for crowdsourced multi-channel recordings," in Proc. IEEE 20th European Signal Processing Conf. (EUSIPCO), 2018.

Paper and audio examples

Concatenative sound synthesis

S. Wager, L Chen, M. Kim, and C. Raphael, "Towards expressive instrument synthesis through smooth frame-by-frame reconstruction: From string to woodwind," In IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), 2017.

Paper and audio examples


Kasten, G., & Wager, S. (2017, November). Learning the pulse: statistical and ML analysis of real-time audio performance logs. Upcoming presentation of summer internship work with Google Android at the Audio Developer Conference, London.

Miksza, P., Watson, K., Zhen, K., & Wager, S. (2017, February). Relationships between experts’ subjective ratings of jazz improvisations and computational measures of melodic entropy. In data analysis phase. Paper presented at the Improvising Brain III: Cultural Variation and Analytical Techniques Symposium, Atlanta, GA.

Raphael, C., Wager, S. Example Application of Approximate Principal Component Analysis to reconstruction of low-quality or de-soloed recordings by imputing spectrum components to the audio, in
McDonald, D. Approximate Principal Components Analysis of Large Data Sets. (2014, September). Presentation at the Department of Statistics, Indiana University.


Under the supervision of Raphael, C. Development of a ‘theremin’ model to represent performance through time-varying pitch and intensity.


INFO-I547/CSCI-B659, Music Information Processing: Audio. 2016, fall session. Instructor: Christopher Raphael.
CSCI-B555, Machine Learning. 2016, spring session. Instructor: Christopher Raphael.
INFO-H101, Honors Introduction to Informatics. 2014 and 2015, fall sessions. Instructor: Nina Onesti.
INFO-I201, Mathematical Foundations of Informatics. 2014, spring and summer sessions. Instructor: Saúl Blanco.
INFO-I101, Introduction to Informatics. 2015, fall session. Instructor: Nina Onesti.

I was nominated for the Computer Science AI of the year award for 2014-2015.