Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition

Abstract

Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models to learn an intermediate deep representation that is both senone-discriminative and domain-invariant. Specifically, the DNN is trained to jointly optimize the primary task of senone classification and the secondary task of domain classification with adversarial objective functions. In this work, instead of only focusing on learning a domain-invariant feature (i.e. the shared component between domains), we also characterize the difference between the source and target domain distributions by explicitly modeling the private component of each domain through a private component extractor DNN. The private component is trained to be orthogonal with the shared component and thus implicitly increases the degree of domain-invariance of the shared component.

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keymeng2017unsupervised

Related papers

• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
• Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
• DEAAN: Disentangled Embedding And Adversarial Adaptation Network For Robust Speaker Representation Learning (2020)9.59
• Domain Adaptation Using Class Similarity For Robust Speech Recognition (2020)6.77
• Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition (2018)0.00
• Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• Self-supervised Learning Based Domain Adaptation For Robust Speaker Verification (2021)11.49