Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition

Abstract

In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6% relative WER reduction.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydenisov2018unsupervised

Related papers

• Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
• Unsupervised Domain Adaptation For Speech Recognition With Unsupervised Error Correction (2022)5.24
• Unsupervised Adaptation With Domain Separation Networks For Robust Speech Recognition (2017)9.92
• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
• Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
• Adversarial Learning Of Raw Speech Features For Domain Invariant Speech Recognition (2018)9.23
• Self-supervised Learning Based Domain Adaptation For Robust Speaker Verification (2021)11.49
• DEAAN: Disentangled Embedding And Adversarial Adaptation Network For Robust Speaker Representation Learning (2020)9.59