Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings
This addresses the problem of robust speaker identification across diverse languages for applications like speech processing, though it is incremental as it builds on existing pre-trained models.
The paper tackled speaker identification in multilingual settings by repurposing the Whisper ASR model's encoder with joint loss optimization, achieving lower equal error rates and higher AUC scores than state-of-the-art baselines across multiple corpora.
Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that repurposes the encoder of the Whisper automatic speech recognition model pre trained on extensive multilingual data to generate robust speaker embeddings via a joint loss optimization strategy that leverages online hard triplet mining and self supervised Normalized Temperature-scaled Cross Entropy loss. By capitalizing on Whisper language-agnostic acoustic representations, our approach effectively distinguishes speakers across diverse languages and recording conditions. Extensive evaluations on multiple corpora, including VoxTube (multilingual), JVS (Japanese), CallHome (German, Spanish, Chinese, and Japanese), and Voxconverse (English), demonstrate that WSI consistently outperforms state-of-the-art baselines, namely Pyannote Embedding, ECAPA TDNN, and Xvector, in terms of lower equal error rates and higher AUC scores. These results validate our hypothesis that a multilingual pre-trained ASR encoder, combined with joint loss optimization, substantially improves speaker identification performance in non-English languages.