MAC Lab Research Talk

Building a community that shares technology, applications, and ideas in audio and music AI.

Overview

We welcome researchers, students, and enthusiasts to join our MAC Lab Research Talk series. This seminar platform is designed to facilitate the exchange of knowledge and foster collaboration in the field of audio and music AI. The topic coverage includes, but is not limited to:

  • Audio / Music AI technology
  • Sound Art: Creation and Production
  • Applications in Audio / Music tech (education, personalization, etc.)
  • Audio / Music Content and Curation
Committee: Junwon Lee, Danbinaerin Han, Sein Lee.


Talk List

  • All
  • -
  • #tech
  • -
  • #art
  • -
  • #application
  • -
  • #content
From Metadata to Al Disclosure: How Global Music Distribution Works
From Metadata to Al Disclosure: How Global Music Distribution Works

Yusik Chung

2026.08.27

#content 

Can Al Judge Good Music? Toward Human-Centric Evaluation of Music Generation
Can Al Judge Good Music? Toward Human-Centric Evaluation of Music Generation

Yonghyun Kim

2026.08.11

#tech 

Everything About Music Curation Channels: From the Growth Strategy of ‘@always_digging’ to Short-Form Consumption Trends
Everything About Music Curation Channels: From the Growth Strategy of ‘@always_digging’ to Short-Form Consumption Trends

Taehyeon Kwon

2026.07.23

#content 

Toward Grounded Audio-Visual Generation: From Speech Dynamics to Physical Sound
Toward Grounded Audio-Visual Generation: From Speech Dynamics to Physical Sound

Hyun-Bin Oh

2026.03.26

#tech 

Bridging Audio and Vision: From Environmental Soundscapes to Speech-driven Faces
Bridging Audio and Vision: From Environmental Soundscapes to Speech-driven Faces

Sung-Bin Kim

2025.12.05

#tech 

소리 시각화 자막: AI를 활용한 소리 뉘앙스 접근성 지원 | Beyond Sound: Al-based Multimodal Music Systems for d/Deaf and Hard-of-Hearing Individuals from Appreciation to Creation and Therapy
소리 시각화 자막: AI를 활용한 소리 뉘앙스 접근성 지원 | Beyond Sound: Al-based Multimodal Music Systems for d/Deaf and Hard-of-Hearing Individuals from Appreciation to Creation and Therapy

JooYeong Kim | Youjin Choi

2025.08.21

#application 

Learning Robust Audio-Language Representations under Data Imbalance | Investigating the Neural and Perceptual Mechanisms of Musical Illusion
Learning Robust Audio-Language Representations under Data Imbalance | Investigating the Neural and Perceptual Mechanisms of Musical Illusion

Yoori Oh | Ahyeon Choi

2025.08.14

#tech 

Towards Multimodal Understanding and Generation of Auditory Scenes
Towards Multimodal Understanding and Generation of Auditory Scenes

Jaeyeon Kim

2025.08.07

#tech 

Multi-modal speech synthesis using face-based speaker identity with enhanced pitch consistency
Multi-modal speech synthesis using face-based speaker identity with enhanced pitch consistency

Jaejun Lee

2025.07.24

#tech