Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixtures

TL;DR

Fx-Encoder++ is a novel model that effectively extracts instrument-specific audio effects representations from music mixtures, enhancing intelligent music production capabilities.

Contribution

The paper introduces Fx-Encoder++, a contrastive learning-based model that transforms mixture-level effects into instrument-wise effects using instrument queries.

Findings

Outperforms previous methods at the mixture level

Successfully extracts instrument-wise effects representations

Improves automatic mixing and effects parameter matching

Abstract

General-purpose audio representations have proven effective across diverse music information retrieval applications, yet their utility in intelligent music production remains limited by insufficient understanding of audio effects (Fx). Although previous approaches have emphasized audio effects analysis at the mixture level, this focus falls short for tasks demanding instrument-wise audio effects understanding, such as automatic mixing. In this work, we present Fx-Encoder++, a novel model designed to extract instrument-wise audio effects representations from music mixtures. Our approach leverages a contrastive learning framework and introduces an "extractor" mechanism that, when provided with instrument queries (audio or text), transforms mixture-level audio effects embeddings into instrument-wise audio effects embeddings. We evaluated our model across retrieval and audio effects parameter matching tasks, testing its performance across a diverse range of instruments. The results demonstrate that Fx-Encoder++ outperforms previous approaches at mixture level and show a novel ability to extract effects representation instrument-wise, addressing a critical capability gap in intelligent music production systems.