Robust speaker recognition using unsupervised adversarial invariance
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.
Code (1)
Tasks
speaker-diarizationSpeaker DiarizationSpeaker RecognitionSpeaker VerificationSimilar Papers 제목 키워드 기반
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task …
Multi-Task LearningSpeaker Recognitionspeech-recognitionSpeech RecognitionAdversarial defense for deep speaker recognition using hybrid adversarial training
Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threat…
Adversarial DefenseSpeaker RecognitionNIESR: Nuisance Invariant End-to-end Speech Recognition
Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e.g., speaker identities, background no…
speech-recognitionSpeech RecognitionAugmentation adversarial training for self-supervised speaker recognition
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance …
Contrastive LearningSpeaker RecognitionChannel adversarial training for speaker verification and diarization
Previous work has encouraged domain-invariance in deep speaker embedding by adversarially classifying the dataset or labelled environment to which the generated features belong. We propose a training strategy which aims …
Speaker Verification