3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization

TL;DR

3D-Speaker-Toolkit is an open-source multimodal framework combining acoustic, semantic, and visual data to enhance speaker verification and diarization accuracy in various environments.

Contribution

It introduces a comprehensive multimodal toolkit with integrated modules and a large dataset, setting a new benchmark for speaker analysis.

Findings

Improved accuracy in speaker verification and diarization.

Effective fusion of acoustic, semantic, and visual modalities.

Open-source toolkit with state-of-the-art models and large dataset.

Abstract

We introduce 3D-Speaker-Toolkit, an open-source toolkit for multimodal speaker verification and diarization, designed for meeting the needs of academic researchers and industrial practitioners. The 3D-Speaker-Toolkit adeptly leverages the combined strengths of acoustic, semantic, and visual data, seamlessly fusing these modalities to offer robust speaker recognition capabilities. The acoustic module extracts speaker embeddings from acoustic features, employing both fully-supervised and self-supervised learning approaches. The semantic module leverages advanced language models to comprehend the substance and context of spoken language, thereby augmenting the system's proficiency in distinguishing speakers through linguistic patterns. The visual module applies image processing technologies to scrutinize facial features, which bolsters the precision of speaker diarization in multi-speaker environments. Collectively, these modules empower the 3D-Speaker-Toolkit to achieve substantially improved accuracy and reliability in speaker-related tasks. With 3D-Speaker-Toolkit, we establish a new benchmark for multimodal speaker analysis. The toolkit also includes a handful of open-source state-of-the-art models and a large-scale dataset containing over 10,000 speakers. The toolkit is publicly available at https://github.com/modelscope/3D-Speaker.