Seungheon Doh

Wootaek Lim

Taejun Kim

Taegyun Kwon

Sangeon Yong

Soonbeom Choi

Saebyul Park

Jongpil Lee

Sangeun Kum

Keunhyoung Kim

Dasaem Jeong

Seunghun Kim

Dabin Kim

Kirak Kim

Hayeon Bang

Junwon Lee

Megan Finch

Yonghyun Kim

Hyeyoon Cho

Jongsoo Kim

Carolina Carusi

Jaeran Choi

Yoonjin Chung

Jiyun Park

Houn Su Kim

Haven Kim

Seolhee Lee

Young June Choi

Jaekwon Im

Eunjin Choi

Joonhyung Bae

Kyungyun Lee

Yoojin Kim

Taewan Kim

Wonil Kim

Minsuk Choi

Jeong Choi

Chaelin Park

Seungsoon Park

Jiyoung Park

Taehyoung Kim

Jangwon Lee

Changheun Oh

The Music and Audio Computing Lab (MACLab) is a research group within the Graduate School of Culture Technology at KAIST. The lab's mission is to enhance music enjoyment, performance, and creation through technological innovation. It focuses on Music AI, aiming to understand music, represent its meanings accessibly, and generate new content to aid human creativity.

KAIST 문화기술대학원 음악 및 오디오 컴퓨팅 연구실(MACLab)은 음악 향유, 연주 및 창작 방식의 개선을 목표로 한다. 음악을 이해하고, 그 의미를 인간 친화적으로 표현하며, 인간의 창의성을 돕는 새로운 음악 콘텐츠 생성에 중점을 둔 음악 AI를 연구한다.

Multimodal deep learning.

Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms

Samplecnn: End-to-end deep convolutional neural networks using very small filters for music classification

EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation

Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging

Deep learning for audio-based music classification and tagging: Teaching computers to distinguish rock from bach

Systems and methods for evaluating strength of an audio password

Sample-level CNN architectures for music auto-tagging using raw waveforms

LP-MusicCaps: LLM-based pseudo music captioning

Comparison and analysis of SampleCNN architectures for audio classification

A Classification-Based Polyphonic Piano Transcription Approach Using Learned Feature Representations.

Raw waveform-based audio classification using sample-level CNN architectures

Learning Sparse Feature Representations for Music Annotation and Retrieval.

Joint detection and classification of singing voice melody using convolutional recurrent neural networks

Graph neural network for music score data and modeling expressive piano performance

Representation learning of music using artist labels

VirtuosoNet: A Hierarchical RNN-based System for Modeling Expressive Piano Performance.

Melody Extraction on Vocal Segments Using Multi-Column Deep Neural Networks.

Systems and methods for audio signal processing

Zero-shot learning for audio-based music classification and tagging

Keunwoo Choi

Honglak Lee

Jiquan Ngiam

Erik Visser

Lae-Hoon Kim

Julius Smith

Kyogu Lee

Aditya Khosla

Andrew Ng

Yi-Hsuan Yang

Vesa Välimäki

saebyul park

Juhan Nam

Appointed as KAIST Endowed Chair Professor for 3 years

Appointed as an associate editor of of the IEEE/ACM Transactions on Audio, Speech, and Language Processing

Professor of the Graduate School of Culture Technology

joins the Graduate School of Culture Technology of KAIST as an adjunct professor

Music and Audio Computing Lab

교수님 소개

남주한

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

연구실 보유 특허

대학별 입시끈

우리 연구실 모집