A Reference-free Metric for Language-Queried Audio Source Separation using Contrastive Language-Audio Pretraining

TL;DR

This paper proposes CLAPScore, a reference-free, semantic similarity-based evaluation metric for language-queried audio source separation that does not require reference signals and considers content relevance.

Contribution

The paper introduces CLAPScore, a novel reference-free evaluation metric using contrastive language-audio pretraining for assessing LASS systems based on semantic relevance.

Findings

CLAPScore correlates well with human judgment of audio relevance.

It outperforms traditional SDR metrics in content-based evaluation.

The metric is publicly available for research use.

Abstract

Language-queried audio source separation (LASS) aims to separate an audio source guided by a text query, with the signal-to-distortion ratio (SDR)-based metrics being commonly used to objectively measure the quality of the separated audio. However, the SDR-based metrics require a reference signal, which is often difficult to obtain in real-world scenarios. In addition, with the SDR-based metrics, the content information of the text query is not considered effectively in LASS. This paper introduces a reference-free evaluation metric using a contrastive language-audio pretraining (CLAP) module, termed CLAPScore, which measures the semantic similarity between the separated audio and the text query. Unlike SDR, the proposed CLAPScore metric evaluates the quality of the separated audio based on the content information of the text query, without needing a reference signal. Experiments show that the CLAPScore provides an effective evaluation of the semantic relevance of the separated audio to the text query, as compared to the SDR metric, offering an alternative for the performance evaluation of LASS systems. The code for evaluation is publicly available.