VoxCeleb1

Overview edit

Variants: VoxCeleb, VoxCeleb1, VoxCeleb1 - 1-shot learning, VoxCeleb1 - 8-shot learning, VoxCeleb1 - 32-shot learning

Associated Benchmarks

This dataset is used in 3 benchmarks:

• Speaker Identification - Metrics: Top-1 (%), Top-5 (%), Number of Params, Accuracy
• Speaker Recognition - Metrics: EER
• Speaker Verification - Metrics: EER

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• Reshape Dimensions Network for Speaker Recognition (2024) -
• SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model (2024) -
• Masked Modeling Duo: Towards a Universal Audio Pre-training Framework (2024) -
• ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models (2024) -
• Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input (2022) -
• Masked Autoencoders that Listen (2022) -
• ATST: Audio Representation Learning with Teacher-Student Transformer (2022) -
• A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding (2021) -
• SSAST: Self-Supervised Audio Spectrogram Transformer (2021) -
• Fine-tuning wav2vec2 for speaker recognition (2021) -
• SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification (2021) -
• Contrastive Learning of General-Purpose Audio Representations (2020) -
• AutoSpeech: Neural Architecture Search for Speaker Recognition (2020) -