Self-supervised Speaker Recognition Training Using Human-Machine Dialogues
This work addresses the challenge of acquiring clean labeled data for speaker recognition, which is important for applications like personalization and authentication, by leveraging noisy human-machine dialogues.
The paper tackled the problem of training speaker recognition models with noisy unlabeled dialogues by proposing a rejection mechanism that selects acoustically homogeneous dialogues for self-supervised pretraining. The result was a 27.10% reduction in equal error rate compared to models without pretraining.
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning, heavily depends on both clean and sufficient labeled data, which is always difficult to acquire. Noisy unlabeled data, on the other hand, also provides valuable information that can be exploited using self-supervised training methods. In this work, we investigate how to pretrain speaker recognition models by leveraging dialogues between customers and smart-speaker devices. However, the supervisory information in such dialogues is inherently noisy, as multiple speakers may speak to a device in the course of the same dialogue. To address this issue, we propose an effective rejection mechanism that selectively learns from dialogues based on their acoustic homogeneity. Both reconstruction-based and contrastive-learning-based self-supervised methods are compared. Experiments demonstrate that the proposed method provides significant performance improvements, superior to earlier work. Dialogue pretraining when combined with the rejection mechanism yields 27.10% equal error rate (EER) reduction in speaker recognition, compared to a model without self-supervised pretraining.