A foundation model for music informatics

[PDF] arxiv.org

From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano

H Zhang, J Liang, S Dixon - arXiv preprint arXiv:2407.04518, 2024 - arxiv.org
Our study investigates an approach for understanding musical performances through the
lens of audio encoding models, focusing on the domain of solo Western classical piano …
相关文章 所有 3 个版本
[PDF] arxiv.org

Audio Conditioning for Music Generation via Discrete Bottleneck Features

S Rouard, Y Adi, J Copet, A Roebel… - arXiv preprint arXiv …, 2024 - arxiv.org
While most music generation models use textual or parametric conditioning (eg tempo,
harmony, musical genre), we propose to condition a language model based music …
相关文章 所有 2 个版本
[PDF] arxiv.org

Embedding Compression for Teacher-to-Student Knowledge Transfer

Y Ding, A Lerch - arXiv preprint arXiv:2402.06761, 2024 - arxiv.org
Common knowledge distillation methods require the teacher model and the student model
to be trained on the same task. However, the usage of embeddings as teachers has also …
相关文章 所有 3 个版本