Few Shot Speaker Recognition using Deep Neural Networks

Abstract

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.

References in corpus (6)

• Prototypical Networks for Few-shot Learning
• Deep Residual Learning for Image Recognition
• VoxCeleb2: Deep Speaker Recognition
• Capsule Network Performance on Complex Data
• CapsNet comparative performance evaluation for image classification
• Learning to match transient sound events using attentional similarity for few-shot sound recognition

Cited by in corpus (9)

• In defence of metric learning for speaker recognition
• Few-Shot Speaker Identification Using Lightweight Prototypical Network with Feature Grouping and Interaction
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• Speaker Recognition Based on Deep Learning: An Overview
• A Study of Few-Shot Audio Classification
• Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition
• Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining
• Few Shot Text-Independent speaker verification using 3D-CNN
• Designing Neural Speaker Embeddings with Meta Learning