4 papers
PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation
Longshen Ou, Ye Wang
This technical report presents a new paradigm for full-song symbolic music generation. Existing symbolic models operate on note-attribute tokens and suffer from extremely long sequ…
Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generation
Longshen Ou, Xichu Ma, Ye Wang
Despite progress in melody-to-lyric generation, a substantial singability gap remains between machine-generated lyrics and those written by human lyricists. In this work, we aim to…
Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization
Longshen Ou, Jingwei Zhao, Ziyu Wang +3
We present a unified framework for automatic multitrack music arrangement that enables a single pre-trained symbolic music model to handle diverse arrangement scenarios, including…
Lead Instrument Detection from Multitrack Music
Longshen Ou, Yu Takahashi, Ye Wang
Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel app…