AutoSpeech: Neural Architecture Search for Speaker Recognition

7 May 2020Shaojin DingTianlong ChenXinyu GongWeiwei ZhaZhangyang Wang

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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Speaker Identification VoxCeleb1 AutoSpeech (N=8,C=128) Top-1 (%) 87.66 # 1
Top-5 (%) 96.01 # 1
Number of Params 18M # 1

Methods used in the Paper