Few Shot Speaker Recognition using Deep Neural Networks
This addresses the challenge of speaker recognition in scenarios where collecting large datasets is impractical, though it is incremental as it builds on existing few-shot learning methods.
The paper tackles the problem of speaker recognition with limited training data by proposing a few-shot learning approach using deep neural networks with prototypical loss and capsule networks, achieving competitive results on public datasets.
The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large amount of data is not possible in practical scenarios. Therefore, in this paper, we propose to identify speakers by learning from only a few training examples. To achieve this, we use a deep neural network with prototypical loss where the input to the network is a spectrogram. For output, we project the class feature vectors into a common embedding space, followed by classification. Further, we show the effectiveness of capsule net in a few shot learning setting. To this end, we utilize an auto-encoder to learn generalized feature embeddings from class-specific embeddings obtained from capsule network. We provide exhaustive experiments on publicly available datasets and competitive baselines, demonstrating the superiority and generalization ability of the proposed few shot learning pipelines.