Audio-based Distributional Semantic Models for Music Auto-tagging and Similarity Measurement

TL;DR

This paper introduces Audio-based Distributional Semantic Models that jointly embed audio and semantic information for improved music auto-tagging and similarity measurement, outperforming existing methods.

Contribution

It presents novel joint acoustic-semantic representations for music, enhancing tag prediction and similarity tasks with superior performance.

Findings

Outperforms state-of-the-art in music similarity measurement

Produces high-quality tags for audio clips

Demonstrates effective joint acoustic-semantic embeddings

Abstract

The recent development of Audio-based Distributional Semantic Models (ADSMs) enables the computation of audio and lexical vector representations in a joint acoustic-semantic space. In this work, these joint representations are applied to the problem of automatic tag generation. The predicted tags together with their corresponding acoustic representation are exploited for the construction of acoustic-semantic clip embeddings. The proposed algorithms are evaluated on the task of similarity measurement between music clips. Acoustic-semantic models are shown to outperform the state-of-the-art for this task and produce high quality tags for audio/music clips.