Centroid-based deep metric learning for speaker recognition
This work addresses speaker recognition for unseen speakers, which is an incremental improvement over existing methods.
The paper tackled the performance gap in speaker recognition between seen and unseen speakers by optimizing a speaker embedding model with prototypical network loss, resulting in improved state-of-the-art performance in verification and identification tasks.
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant performance gap between recognizing speakers in the training set and unseen speakers. The latter case corresponds to the few-shot learning task, where a trained model is evaluated on unseen classes. Here, we optimize a speaker embedding model with prototypical network loss (PNL), a state-of-the-art approach for the few-shot image classification task. The resulting embedding model outperforms the state-of-the-art triplet loss based models in both speaker verification and identification tasks, for both seen and unseen speakers.