Delving Into Voxceleb: Environment Invariant Speaker Recognition

Abstract

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful architectures or loss functions suitable for the task, but these works do not consider what information is learnt by the models, apart from being able to predict the given labels. In this work, we introduce an environment adversarial training framework in which the network can effectively learn speaker-discriminative and environment-invariant embeddings without explicit domain shift during training. We achieve this by utilising the previously unused `video' information in the VoxCeleb dataset. The environment adversarial training allows the network to generalise better to unseen conditions. The method is evaluated on both speaker identification and verification tasks using the VoxCeleb dataset, on which we demonstrate significant performance improvements ov

Stats

• citations23
• S2 citations—
• github stars0
• HF likes0
• heat score10.35
• arxiv keychung2019delving

Related papers

• Voxceleb2: Deep Speaker Recognition (2018)23.96
• The Ins And Outs Of Speaker Recognition: Lessons From Voxsrc 2020 (2020)11.85
• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• Disentangled Representation Learning For Environment-agnostic Speaker Recognition (2024)4.82
• Within-sample Variability-invariant Loss For Robust Speaker Recognition Under Noisy Environments (2020)11.85
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• Voxceleb: A Large-scale Speaker Identification Dataset (2017)23.55
• Channel Adversarial Training For Speaker Verification And Diarization (2019)7.50