arXiv (Cornell University) · 2020 · 35 citations · 31 references
Open access
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningSelf-supervised LearningSpeaker IdentificationSpeech AcousticsSpeech RecognitionUnsupervised LearningAutoencodersChannel State InformationContrastive LearningData AugmentationRobust Speech RecognitionSelf-supervised Speech Representation LearningSpeaker Recognition
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be similar and across-utterance embeddings to be dissimilar. However, since the within-utterance segments share the same acoustic characteristics, it is difficult to separate the speaker information from the channel information. To this end, we propose augmentation adversarial training strategy that trains the network to be discriminative for the speaker information, while invariant to the augmentation applied. Since the augmentation simulates the acoustic characteristics, training the network to be invariant to augmentation also encourages the network to be invariant to the channel information in general. Extensive experiments on the VoxCeleb and VOiCES datasets show significant improvements over previous works using self-supervision, and the performance of our self-supervised models far exceed that of humans.
31
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
Kaldi Speech Recognition Toolkit
Daniel Povey · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2024 · 4.9K citations · Full text
Computing, Linguistics, Acoustics +15
Front-End Factor Analysis for Speaker Verification
Najim Dehak, Patrick Kenny, Réda Dehak et al. · IEEE Transactions on Audio Speech and Language Processing · 2010 · 3.6K citations