VoxCeleb2: Deep speaker recognition
<p>The objective of this paper is speaker recognition under noisy and unconstrained conditions.</p> <br/> <p>We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automate...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
International Speech Communication Association
2018
|
| _version_ | 1797052106929078272 |
|---|---|
| author | Chung, J Nagrani, A Zisserman, A |
| author_facet | Chung, J Nagrani, A Zisserman, A |
| author_sort | Chung, J |
| collection | OXFORD |
| description | <p>The objective of this paper is speaker recognition under noisy and unconstrained conditions.</p> <br/> <p>We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset.</p> <br/> <p>Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under various conditions. The models trained on the VoxCeleb2 dataset surpass the performance of previous works on a benchmark dataset by a significant margin.</p> |
| first_indexed | 2024-03-06T18:28:04Z |
| format | Conference item |
| id | oxford-uuid:08ab75c5-aa1c-49fc-b36a-1280c6a309c4 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:28:04Z |
| publishDate | 2018 |
| publisher | International Speech Communication Association |
| record_format | dspace |
| spelling | oxford-uuid:08ab75c5-aa1c-49fc-b36a-1280c6a309c42022-03-26T09:14:09ZVoxCeleb2: Deep speaker recognitionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:08ab75c5-aa1c-49fc-b36a-1280c6a309c4Symplectic Elements at OxfordInternational Speech Communication Association2018Chung, JNagrani, AZisserman, A<p>The objective of this paper is speaker recognition under noisy and unconstrained conditions.</p> <br/> <p>We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset.</p> <br/> <p>Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under various conditions. The models trained on the VoxCeleb2 dataset surpass the performance of previous works on a benchmark dataset by a significant margin.</p> |
| spellingShingle | Chung, J Nagrani, A Zisserman, A VoxCeleb2: Deep speaker recognition |
| title | VoxCeleb2: Deep speaker recognition |
| title_full | VoxCeleb2: Deep speaker recognition |
| title_fullStr | VoxCeleb2: Deep speaker recognition |
| title_full_unstemmed | VoxCeleb2: Deep speaker recognition |
| title_short | VoxCeleb2: Deep speaker recognition |
| title_sort | voxceleb2 deep speaker recognition |
| work_keys_str_mv | AT chungj voxceleb2deepspeakerrecognition AT nagrania voxceleb2deepspeakerrecognition AT zissermana voxceleb2deepspeakerrecognition |