VoxCeleb

doi:doi:10.57702/9zson5bd

VoxCeleb

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker characteristics from short utterances.

BibTex:

@dataset{Arsha_Nagrani_and_Joon_Son_Chung_and_Andrew_Zisserman_2024,
    abstract = {Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker characteristics from short utterances.},
    author = {Arsha Nagrani and Joon Son Chung and Andrew Zisserman},
    doi = {10.57702/9zson5bd},
    institution = {No Organization},
    keyword = {' VoxCeleb', '1251 speakers', 'ASV', 'Audio', 'Audio Data', 'Audio Features', 'Audio-Visual Dataset', 'Broadcast News', 'COVID-19 Detection', 'Celebrities', 'Celebrity Interviews', 'Emotion Recognition', 'Large-Scale Dataset', 'Multimodal Emotion Recognition', 'Multispeaker TTS', 'Sex Classification', 'Speaker Identification', 'Speaker Recognition', 'Speaker Verification', 'Speech Emotion Recognition', 'Speech Recognition', 'Text Emotion Recognition', 'VoxCeleb', 'VoxCeleb1', 'VoxCeleb2', 'YouTube', 'YouTube interviews', 'audio', 'audio-visual style transfer', 'driving videos', 'image animation', 'large-scale dataset', 'multimodal learning', 'speaker identification', 'speaker recognition', 'speaker verification', 'speech recognition', 'static images', 'voice aging', 'voice recognition', 'voxceleb'},
    month = {dec},
    publisher = {TIB},
    title = {VoxCeleb},
    url = {https://service.tib.eu/ldmservice/dataset/voxceleb},
    year = {2024}
}