Within-sample Variability-invariant Loss For Robust Speaker Recognition Under Noisy Environments

Abstract

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding of the noisy utterance. Specifically, the network is trained with the original speaker identification loss with an auxiliary within-sample variability-invariant loss. This auxiliary variability-invariant loss is used to learn the same embedding among the clean utterance and its noisy copies and prevents the network from encoding the undesired noises or variabilities into the speaker representation. Furthermore, we investigate the data preparation strategy for generating clean and noisy utterance pairs on-the-fly. The strategy generates different noisy copies for the same clean utterance at each training step, helping the speaker embedding network generalize better under noisy environments. Experiments on VoxCeleb1 indicate that the proposed training

Stats

• citations37
• S2 citations—
• github stars0
• HF likes0
• heat score11.85
• arxiv keycai2020within

Related papers

• A Joint Noise Disentanglement And Adversarial Training Framework For Robust Speaker Verification (2024)6.34
• Delving Into Voxceleb: Environment Invariant Speaker Recognition (2019)10.35
• Disentangled Speaker And Nuisance Attribute Embedding For Robust Speaker Verification (2020)8.60
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• Margin Matters: Towards More Discriminative Deep Neural Network Embeddings For Speaker Recognition (2019)15.25
• Length- And Noise-aware Training Techniques For Short-utterance Speaker Recognition (2020)0.00
• Robust Speaker Recognition Using Unsupervised Adversarial Invariance (2019)9.76
• Noise-conditioned Mixture-of-experts Framework For Robust Speaker Verification (2025)0.00