Sangeun Kum

Publication Activity (10 Years)

Years Active: 2016-2022
Publications (10 Years): 9

Top Topics

Supervised Learning

Labeled And Unlabeled Data

Student Modelling

Top Venues

Publications

Sangeun Kum, Jongpil Lee, Keunhyoung Luke Kim, Taehyoung Kim, Juhan Nam
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music. ICASSP (2022)
Sangeun Kum, Jongpil Lee, Keunhyoung Luke Kim, Taehyoung Kim, Juhan Nam
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic Music. CoRR (2022)
Keunhyoung Luke Kim, Jongpil Lee, Sangeun Kum, Juhan Nam
Learning a cross-domain embedding space of vocal and mixed audio with a structure-preserving triplet loss. ISMIR (2021)
Keunhyoung Luke Kim, Jongpil Lee, Sangeun Kum, Chae Lin Park, Juhan Nam
Semantic Tagging of Singing Voices in Popular Music Recordings. IEEE ACM Trans. Audio Speech Lang. Process. 28 (2020)
Sangeun Kum, Jing-Hua Lin, Li Su, Juhan Nam
Semi-supervised learning using teacher-student models for vocal melody extraction. ISMIR (2020)
Sangeun Kum, Jing-Hua Lin, Li Su, Juhan Nam
Semi-supervised learning using teacher-student models for vocal melody extraction. CoRR (2020)
Jiyoung Park, Donghyun Kim, Jongpil Lee, Sangeun Kum, Juhan Nam
A Hybrid of Deep Audio Feature and i-vector for Artist Recognition. CoRR (2018)
Jongpil Lee, Jiyoung Park, Sangeun Kum, Youngho Jeong, Juhan Nam
Combining Multi-Scale Features Using Sample-Level Deep Convolutional Neural Networks for Weakly Supervised Sound Event Detection. DCASE (2017)
Sangeun Kum, Changheun Oh, Juhan Nam
Melody Extraction on Vocal Segments Using Multi-Column Deep Neural Networks. ISMIR (2016)