Research Projects

Anastasia Kuznetsova, Aswin Sivaraman, and Minje Kim, “The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),…

Paper Haici Yang, Wootaek Lim, and Minje Kim, "Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding," in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal…

Neural Pitch Correction of Singing VoiceSpatially-Informed Music Source SeparationNeural Music RemixingNeural Music Upmixing

Title Upmixing via Style Transfer: a Variational Autoencoder for Disentangling Spatial Images and Musical Content Authors Haici Yang, Sanna Wager, Spencer Russell, Mike Luo, Minje Kim, and Wontak Kim Abstract…

Source codes can be found at: https://github.com/cocosci/NSC Speaker ID: DR5-MBPM0-SA1 System Low Bitrate Mid Bitrate High Bitrate Reference LPF 4kHz Model I Model II Model III Model IV AMR-WB Opus…