minje, Author at Minje Kim's Home

How to Prepare for the Technical Presentation?: A Short Lecture at a Conference

[latexpage] While people around me realize how fun attending a conference is, especially after the COVID-19 pandemic, I also found that not "everyone" can truly enjoy such an academic event.…

minje September 18, 2025

Research Projects

AD-FlowTSE: Adaptive Deterministic Flow Matching for Target Speaker Extraction

Imagine being in a crowded room where several people are speaking at the same time. Yet somehow, your brain can focus on a single voice you care about and filter…

minje September 17, 2025

Research Projects

From Hallucination to Articulation: Language Model-Driven Losses for Neural Speech Coding

Motivation Ultra-low-bitrate neural speech codecs have made remarkable progress in recent years. Modern systems can operate at a few hundred bits per second while maintaining surprisingly good perceptual quality. However,…

minje September 17, 2025

News Pictures

Darius Defended

Darius Petermann successfully defended his dissertation on "Efficient Native Neural Sub-band Coding through Residual Feature Representation within Hyper-Autoencoded Reconstruction Propagation Networks."

minje September 6, 2025

Featured Projects Research Projects

TGIF: A Family-Owned Voice AI

Overview In everyday life, our devices run many speech/audio applications that can benefit from the target speaker extraction (TSE) concept: the ability to pull out your voice from a noisy mixture of sounds.…

minje July 11, 2025

Featured Projects Research Projects

Audio Coding for Machines

Machine-Learned Latent Features Are Codes for That Machine! When we think about compressing sound, we usually imagine MP3s or AACs, or even neural codecs with a higher compression ratio these…

minje July 11, 2025

News Pictures

Fraunhofer IIS and AudioLabs in Erlangen

The visit to Fraunhofer IIS and International Audio Labs in Erlangen was so inspiring and heartwarming. Introducing my neural audio coding works to the leading experts in audio coding was…

minje July 10, 2025

News Pictures

University of Hamburg

It was such a nice visit to Timo Gerkmann's signal processing group at the University of Hamburg. I had a great time speaking with the bright students and researchers there,…

minje July 8, 2025

News

WASPAA 2025

Four papers were accepted for publication at WASPAA 2025: Anastasia Kuznetsova, Inseon Jang, Wootaek Lim, Minje Kim, "Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine"…

minje July 3, 2025

News Pictures

Ajou Honorary Alumni

I was recognized as "Ajou Honorary Alumni" by my alma mater, Ajou University, along with my then-girlfriend-now-wife Kahyun Choi.

minje June 30, 2025