Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition

Abstract

Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of labeled data is necessary, which are often expensive to obtain. This paper explores the application of adversarial training to learn features from raw speech that are invariant to acoustic variability. This acoustic variability is referred to as a domain shift in this paper. The experimental study presented in this paper leverages the architecture of Domain Adversarial Neural Networks (DANNs) [1] which uses data from two different domains. The DANN is a Y-shaped network that consists of a multi-layer CNN feature extractor module that is common to a label (senone) classifier and a so-called domain classifier. The utility of DANNs is evaluated on multiple datasets with domain shifts caused due to differences in gender and speaker accents. Promising em

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keytripathi2018adversarial

Related papers

• Domain Adversarial Neural Networks For Dysarthric Speech Recognition (2020)7.50
• Attentive Adversarial Learning For Domain-invariant Training (2019)6.77
• Adversarial Training For Multi-domain Speaker Recognition (2020)6.77
• Domain Adversarial Learning For Emotion Recognition (2019)0.00
• Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition (2017)9.92
• Extracting Domain Invariant Features By Unsupervised Learning For Robust Automatic Speech Recognition (2018)9.03
• Unsupervised Cross-lingual Speech Emotion Recognition Using Domainadversarial Neural Network (2020)0.00
• Toward Domain-invariant Speech Recognition Via Large Scale Training (2018)13.39