Few Shot Text-Independent speaker verification using 3D-CNN
This addresses the challenge of speaker verification for audio biometrics in scenarios where text-independent data is scarce, representing an incremental improvement in a domain-specific area.
The paper tackles the problem of text-independent speaker verification with very limited training data by proposing a novel method using a Siamese neural network with center loss and speaker bias loss, achieving accuracy near state-of-the-art models on the VoxCeleb1 dataset.
Facial recognition system is one of the major successes of Artificial intelligence and has been used a lot over the last years. But, images are not the only biometric present: audio is another possible biometric that can be used as an alternative to the existing recognition systems. However, the text-independent audio data is not always available for tasks like speaker verification and also no work has been done in the past for text-independent speaker verification assuming very little training data. Therefore, In this paper, we have proposed a novel method to verify the identity of the claimed speaker using very few training data. To achieve this we are using a Siamese neural network with center loss and speaker bias loss. Experiments conducted on the VoxCeleb1 dataset show that the proposed model accuracy even on training with very few data is near to the state of the art model on text-independent speaker verification