Bridging Language Gaps in Audio-Text Retrieval

TL;DR

This paper introduces a multilingual audio-text retrieval method that enhances language support and achieves state-of-the-art results in English and multiple other languages with minimal additional data.

Contribution

It proposes a novel language enhancement technique using a multilingual encoder and a consistent ensemble distillation approach to improve cross-lingual audio-text retrieval.

Findings

State-of-the-art performance on AudioCaps and Clotho datasets.

Effective retrieval in seven languages with only 10% extra training data.

Supports variable-length audio-text retrieval efficiently.

Abstract

Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data. To address these linguistic disparities, we propose a language enhancement (LE), using a multilingual text encoder (SONAR) to encode the text data with language-specific information. Additionally, we optimize the audio encoder through the application of consistent ensemble distillation (CED), enhancing support for variable-length audio-text retrieval. Our methodology excels in English audio-text retrieval, demonstrating state-of-the-art (SOTA) performance on commonly used datasets such as AudioCaps and Clotho. Simultaneously, the approach exhibits proficiency in retrieving content in seven other languages with only 10% of additional language-enhanced training data, yielding promising results. The source code is publicly available https://github.com/zyyan4/ml-clap.