VoxCeleb

VoxCeleb is a dataset containing naturally noisy speech recordings used to evaluate the generalization of speech separation systems in real-world scenarios.

Papers using VoxCeleb (39)

CAM++: A Fast And Efficient Network For Speaker Verification Using Context-aware Masking2023 · 124 citesMFA: TDNN With Multi-scale Frequency-channel Attention For Text-independent Speaker Verification With Short Utterances2022 · 71 citesLeveraging ASR Pretrained Conformers For Speaker Verification Through Transfer Learning And Knowledge Distillation2023 · 26 citesConvolution-based Channel-frequency Attention For Text-independent Speaker Verification2022 · 12 citesEditnet: A Lightweight Network For Unsupervised Domain Adaptation In Speaker Verification2022 · 9 citesSelf-distillation Prototypes Network: Learning Robust Speaker Representations Without Supervision2023 · 3 citesTASLA: Text-Aligned Speech Tokens with Multiple Layer-Aggregation2025 · 2 citesModel Compression For Dnn-based Speaker Verification Using Weight Quantization2022 · 2 citesNonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech2025 · 1 citesDisentangling Voice And Content With Self-supervision For Speaker Recognition2023 · 5 citesRing Mixing with Auxiliary Signal-to-Consistency-Error Ratio Loss for Unsupervised Denoising in Speech Separation2026Vclip: Face-based Speaker Generation by Face-voice Association Learning2026Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification2025Magnitude and Phase-based Feature Fusion Using Co-attention Mechanism for Speaker recognition2025Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification2025Short-Segment Speaker Verification with Pre-trained Models and Multi-Resolution Encoder2025Clustering-based hard negative sampling for supervised contrastive speaker verification2025MGFF-TDNN: A Multi-granularity Feature Fusion TDNN Model With Depth-wise Separable Module For Speaker Verification2025MGFF-TDNN: A Multi-Granularity Feature Fusion TDNN Model with Depth-Wise Separable Module for Speaker Verification2025Improving Transformer-based Networks With Locality For Automatic Speaker Verification2023 · 18 citesSE/BN Adapter: Parametric Efficient Domain Adaptation For Speaker Recognition2024 · 1 citesSelf-film: Conditioning Gans With Self-supervised Representations For Bandwidth Extension Based Speaker Recognition2023Laugh Betrays You? Learning Robust Speaker Representation From Speech Containing Non-verbal Fragments2022Disentangling Voice and Content with Self-Supervision for Speaker Recognition2023 · 5 citesCAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking2023 · 3 citesConvolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification2022 · 1 citesEDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification2022Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning2022Toroidal Probabilistic Spherical Discriminant Analysis2022Laugh Betrays You? Learning Robust Speaker Representation From Speech Containing Non-Verbal Fragments2022Model Compression for DNN-based Speaker Verification Using Weight Quantization2022Distance-based Weight Transfer from Near-field to Far-field Speaker Verification2023Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition2023Ordered and Binary Speaker Embedding2023Leveraging ASR Pretrained Conformers for Speaker Verification through Transfer Learning and Knowledge Distillation2023SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition2024AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling2024M-Vec: Matryoshka Speaker Embeddings with Flexible Dimensions2024Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions2024