Robust speaker recognition using unsupervised adversarial invariance
This work addresses the problem of speaker recognition for applications in noisy or variable acoustic environments, representing an incremental advancement over existing methods.
The paper tackles robust speaker recognition in challenging acoustic conditions by using an unsupervised adversarial invariance method to extract speaker-discriminative embeddings, resulting in substantial performance improvements including a 36% relative reduction in diarization error rate compared to state-of-the-art baselines.
In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial invariance architecture to train a network that maps speaker embeddings extracted using a pre-trained model onto two lower dimensional embedding spaces. The embedding spaces are learnt to disentangle speaker-discriminative information from all other information present in the audio recordings, without supervision about the acoustic conditions. We analyze the robustness of the proposed embeddings to various sources of variability present in the signal for speaker verification and unsupervised clustering tasks on a large-scale speaker recognition corpus. Our analyses show that the proposed system substantially outperforms the baseline in a variety of challenging acoustic scenarios. Furthermore, for the task of speaker diarization on a real-world meeting corpus, our system shows a relative improvement of 36\% in the diarization error rate compared to the state-of-the-art baseline.