Autoencoder based Domain Adaptation for Speaker Recognition under Insufficient Channel Information
This addresses domain adaptation for speaker recognition in real-life conditions where limited data hinders channel estimation, representing an incremental advancement.
The paper tackles performance degradation in speaker recognition due to domain mismatch when channel information is insufficient, proposing an Autoencoder based Domain Adaptation (AEDA) approach that shows significant improvements over baselines and prior studies on the Domain Adaptation Challenge 13 protocols.
In real-life conditions, mismatch between development and test domain degrades speaker recognition performance. To solve the issue, many researchers explored domain adaptation approaches using matched in-domain dataset. However, adaptation would be not effective if the dataset is insufficient to estimate channel variability of the domain. In this paper, we explore the problem of performance degradation under such a situation of insufficient channel information. In order to exploit limited in-domain dataset effectively, we propose an unsupervised domain adaptation approach using Autoencoder based Domain Adaptation (AEDA). The proposed approach combines an autoencoder with a denoising autoencoder to adapt resource-rich development dataset to test domain. The proposed technique is evaluated on the Domain Adaptation Challenge 13 experimental protocols that is widely used in speaker recognition for domain mismatched condition. The results show significant improvements over baselines and results from other prior studies.