Posted inNews
Anastasia Proposed Dissertation
Anastasia proposed her dissertation successfully.
Posted inNews
WASPAA, SANE, and AES
Minje attended WASPAA 2023 as the general co-chair. Anastasia presented her poster at SANE. Minje was on the panel discussion at AES. All in the third week of Oct 2023,…
Posted inNews
JSTSP Special Issue
IEEE JSTSP accepted the special issue proposal on neural speech and audio coding, which Minje contributed to as a guest editor along with Jan Skoglund (Lead GE, Google), Xiulian Peng…
Posted inFeatured Projects Research Projects
Scalable and Efficient Speech Enhancement Using Modified Cold Diffusion
[latexpage] As we've proposed in the BLOOM-Net project, scalability matters. Just to reiterate the argument here once again, the main issue with the current deep learning-based models for speech enhancement…
Hyperbolic Distance-Based Speech Separation
Paper Darius Petermann and Minje Kim, “Hyperbolic Distance-Based Speech Separation,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Seoul, Korea, Apr. 14-19, 2024 [pdf]. Audio Example #1…
Posted inFeatured Projects Research Projects
LaDiffCodec: Generative De-Quantization for Neural Speech Codec via Latent Diffusion
[latexpage] Motivation We bring the cool generative power of a diffusion model to speech coding. We call our codec LaDiffCodec as it is actively using the concept of latent diffusion((R.…
Posted inNews
HSCMA 2024
Minje's proposal to organize the Hands-free Speech Communication and Microphone Array (HSCMA) is accepted. It will be a satellite workshop of ICASSP 2024 in Seoul. Minje co-organizes this workshop with…
