Attentive Adversarial Learning For Domain-invariant Training

Abstract

Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary domain classifier takes in equally-weighted deep features from a deep neural network (DNN) acoustic model and is trained to improve their domain-invariance by optimizing an adversarial loss function. In this work, we propose an attentive ADIT (AADIT) in which we advance the domain classifier with an attention mechanism to automatically weight the input deep features according to their importance in domain classification. With this attentive re-weighting, AADIT can focus on the domain normalization of phonetic components that are more susceptible to domain variability and generates deep features with improved domain-invariance and senone-discriminativity over ADIT. Most importantly, the attention block serves only as an external component to the DNN acoust

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keymeng2019attentive

Related papers

• Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
• Domain Adversarial Training For Accented Speech Recognition (2018)13.84
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• End-to-end Domain-adversarial Voice Activity Detection (2019)10.35
• Speaker-independent Acoustic-to-articulatory Inversion Through Multi-channel Attention Discriminator (2024)0.00
• Domain Adversarial Neural Networks For Dysarthric Speech Recognition (2020)7.50
• Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition (2017)9.92
• Adversarial Training Improves Generalization Under Distribution Shifts In Bioacoustics (2025)0.00