Paper Info
Title
Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans
Abstract
Current speaker recognition technology provides great performance with the x-vector approach. However, performance decreases when the evaluation domain is different from the training domain, an issue usually addressed with domain adaptation approaches. Recently, unsupervised domain adaptation using cycle-consistent Generative Adversarial Networks (CycleGAN) has received a lot of attention. Cycle-GAN learn mappings between features of two domains given non-parallel data. We investigate their effectiveness in low resource scenario i.e. when limited amount of target domain data is available for adaptation, a case unexplored in previous works. We experiment with two adaptation tasks: microphone to telephone and a novel reverberant to clean adaptation with the end goal of improving speaker recognition performance. Number of speakers present in source and target domains are 7000 and 191 respectively. By adding noise to the target domain during CycleGAN training, we were able to achieve better performance compared to the adaptation system whose CycleGAN was trained on a larger target data. On reverberant to clean adaptation task, our models improved EER by 18.3% relative on VOiCES dataset compared to a system trained on clean data. They also slightly improved over the state-of-the-art Weighted Prediction Error (WPE) de-reverberation algorithm.
Year
DOI
Venue
2019
10.1109/ASRU46091.2019.9003748
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
Keywords
Field
DocType
Domain Adaptation,CycleGAN,Low Resource,Microphone-Telephone,Speaker Recognition
Mean squared prediction error,Computer science,Domain adaptation,Speech recognition,Speaker recognition,Generative grammar,Microphone
Conference
ISBN
Citations 
PageRank 
978-1-7281-0307-5
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Phani S. Nidadavolu1113.78
Saurabh Kataria295.21
jesus villalba3415.11
N. Dehak4126992.64