Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Delving into VoxCeleb: environment invariant speaker recognition

About

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful architectures or loss functions suitable for the task, but these works do not consider what information is learnt by the models, apart from being able to predict the given labels. In this work, we introduce an environment adversarial training framework in which the network can effectively learn speaker-discriminative and environment-invariant embeddings without explicit domain shift during training. We achieve this by utilising the previously unused `video' information in the VoxCeleb dataset. The environment adversarial training allows the network to generalise better to unseen conditions. The method is evaluated on both speaker identification and verification tasks using the VoxCeleb dataset, on which we demonstrate significant performance improvements over baselines.

Joon Son Chung, Jaesung Huh, Seongkyu Mun• 2019

Related benchmarks

TaskDatasetResultRank
Speaker IdentificationVoxCeleb1
Accuracy89
58
Showing 1 of 1 rows

Other info

Follow for update