Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation

Abstract

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world applications. Research on robust speech recognition can be regarded as trying to overcome this domain mismatch issue. In this paper, we address the unsupervised domain adaptation problem for robust speech recognition, where both source and target domain speech are presented, but word transcripts are only available for the source domain speech. We present novel augmentation-based methods that transform speech in a way that does not change the transcripts. Specifically, we first train a variational autoencoder on both source and target domain data (without supervision) to learn a latent representation of speech. We then transform nuisance attributes of speech that are irrelevant to recognition by modifying the latent representations, in order to augment lab

Stats

• citations78
• S2 citations—
• github stars0
• HF likes0
• heat score14.23
• arxiv keyhsu2017unsupervised

Related papers

• Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
• A Study Of Enhancement, Augmentation, And Autoencoder Methods For Domain Adaptation In Distant Speech Recognition (2018)8.60
• Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition (2017)9.92
• Self-supervised Learning Based Domain Adaptation For Robust Speaker Verification (2021)11.49
• Extracting Domain Invariant Features By Unsupervised Learning For Robust Automatic Speech Recognition (2018)9.03
• Analyzing The Robustness Of Unsupervised Speech Recognition (2021)7.81
• Autoencoder Based Domain Adaptation For Speaker Recognition Under Insufficient Channel Information (2017)10.07
• Vae-based Domain Adaptation For Speaker Verification (2019)7.50