AutoSpeech: Neural Architecture Search for Speaker Recognition

Abstract

Speaker recognition systems based on Convolutional Neural Networks (CNNs) are often built with off-the-shelf backbones such as VGG-Net or ResNet. However, these backbones were originally proposed for image classification, and therefore may not be naturally fit for speaker recognition. Due to the prohibitive complexity of manually exploring the design space, we propose the first neural architecture search approach approach for the speaker recognition tasks, named as AutoSpeech. Our algorithm first identifies the optimal operation combination in a neural cell and then derives a CNN model by stacking the neural cell for multiple times. The final speaker recognition model can be obtained by training the derived CNN model through the standard scheme. To evaluate the proposed approach, we conduct experiments on both speaker identification and speaker verification tasks using the VoxCeleb1 dataset. Results demonstrate that the derived CNN architectures from the proposed approach significantly outperform current speaker recognition systems based on VGG-M, ResNet-18, and ResNet-34 back-bones, while enjoying lower model complexity.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Architecture Search with Reinforcement Learning
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Efficient Neural Architecture Search via Parameter Sharing
• Deep Speaker: an End-to-End Neural Speaker Embedding System
• DeepArchitect: Automatically Designing and Training Deep Architectures
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System
• Leveraging End-to-End Speech Recognition with Neural Architecture Search

Cited by in corpus (9)

• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
• Speaker Recognition Based on Deep Learning: An Overview
• AutoKWS: Keyword Spotting with Differentiable Architecture Search
• VINNAS: Variational Inference-based Neural Network Architecture Search
• Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients
• Latency-Controlled Neural Architecture Search for Streaming Speech Recognition