2020 · 399 citations · 37 references
ComputingComputer ScienceFeature EngineeringMachine LearningPhoneticsDeep LearningLoss FunctionMetric LearningOptimization For Machine LearningRepresentation LearningSpeech RecognitionMetric Learning For ClassificationOpen-set Speech Recognition TrainingSpeaker RecognitionTriplet LossTriplet Networks
The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-speaker distance. A popular belief in speaker recognition is that networks trained with classification objectives outperform metric learning methods. In this paper, we present an extensive evaluation of most popular loss functions for speaker recognition on the VoxCeleb dataset. We demonstrate that the vanilla triplet loss shows competitive performance compared to classification-based losses, and those trained with our proposed metric learning objective outperform state-of-the-art methods.
37
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Adam Paszke, Sam Gross, Francisco Massa et al. · arXiv (Cornell University) · 2019 · 16.2K citations · Full text
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text