SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Jiaye, Luo, Haonan, Song, Linfeng, Chen, Shuaiqi, Lyu, Yishan, Zhong, Zian, Wang, Roujia, Jiang, Daniel, Zhang, Haoran, Bai, Jiaming, Cheng, Haoran, Liao, Q. Vera, Dong, Hao-Wen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914093410025472
author Tan, Jiaye
Luo, Haonan
Song, Linfeng
Chen, Shuaiqi
Lyu, Yishan
Zhong, Zian
Wang, Roujia
Jiang, Daniel
Zhang, Haoran
Bai, Jiaming
Cheng, Haoran
Liao, Q. Vera
Dong, Hao-Wen
author_facet Tan, Jiaye
Luo, Haonan
Song, Linfeng
Chen, Shuaiqi
Lyu, Yishan
Zhong, Zian
Wang, Roujia
Jiang, Daniel
Zhang, Haoran
Bai, Jiaming
Cheng, Haoran
Liao, Q. Vera
Dong, Hao-Wen
contents Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We propose Attribute-Specialized Key-Value Head Sharing (AS-KVHS), adapted to music's structured symbolic representation, achieving about 30% inference speedup with only a negligible (about 0.4%) quality drop in objective evaluations and slight improvements in subjective listening tests. Our main contributions are (1) the first systematic study of BPE's generalizability in multi-track symbolic music, and (2) the introduction of AS-KVHS for low-latency symbolic music generation. Beyond these, we also release SAGE-Music, an open-source benchmark that matches or surpasses state-of-the-art models in generation quality.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
Tan, Jiaye
Luo, Haonan
Song, Linfeng
Chen, Shuaiqi
Lyu, Yishan
Zhong, Zian
Wang, Roujia
Jiang, Daniel
Zhang, Haoran
Bai, Jiaming
Cheng, Haoran
Liao, Q. Vera
Dong, Hao-Wen
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We propose Attribute-Specialized Key-Value Head Sharing (AS-KVHS), adapted to music's structured symbolic representation, achieving about 30% inference speedup with only a negligible (about 0.4%) quality drop in objective evaluations and slight improvements in subjective listening tests. Our main contributions are (1) the first systematic study of BPE's generalizability in multi-track symbolic music, and (2) the introduction of AS-KVHS for low-latency symbolic music generation. Beyond these, we also release SAGE-Music, an open-source benchmark that matches or surpasses state-of-the-art models in generation quality.
title SAGE-Music: Low-Latency Symbolic Music Generation via Attribute-Specialized Key-Value Head Sharing
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2510.00395