activity
20152022
most citedSpecTNT: a Time-Frequency Transformer for Music Audio

14 citations · 23 across the 9 of their papers we have counts for

collaborators

9 papers

cs.SD20221 cited

MuSFA: Improving Music Structural Function Analysis with Partially Labeled Data

Ju-Chiang Wang, Jordan B. L. Smith, Yun-Ning Hung

Music structure analysis (MSA) systems aim to segment a song recording into non-overlapping sections with useful labels. Previous MSA systems typically predict abstract labels in a…

cs.SD20222 cited

Binaural Rendering of Ambisonic Signals by Neural Networks

Yin Zhu, Qiuqiang Kong, Junjie Shi +4

Binaural rendering of ambisonic signals is of broad interest to virtual reality and immersive media. Conventional methods often require manually measured Head-Related Transfer Func…

cs.SD2022

Modeling Beats and Downbeats with a Time-Frequency Transformer

Yun-Ning Hung, Ju-Chiang Wang, Xuchen Song +2

Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music information retrieval (M…

eess.AS20221 cited

To catch a chorus, verse, intro, or anything else: Analyzing a song with structural functions

Ju-Chiang Wang, Yun-Ning Hung, Jordan B. L. Smith

Conventional music structure analysis algorithms aim to divide a song into segments and to group them with abstract labels (e.g., 'A', 'B', and 'C'). However, explicitly identifyin…

cs.SD202114 cited

SpecTNT: a Time-Frequency Transformer for Music Audio

Wei-Tsung Lu, Ju-Chiang Wang, Minz Won +2

Transformers have drawn attention in the MIR field for their remarkable performance shown in natural language processing and computer vision. However, prior works in the audio proc…

eess.AS20212 cited

Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-task Learning

Ju-Chiang Wang, Jordan B. L. Smith, Jitong Chen +2

This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised, with pipelines desig…