Domain Adaptation Of Low-resource Target-domain Models Using Well-trained ASR Conformer Models

Abstract

In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large dataset is available. We argue that in the encoder-decoder framework, the decoder of the well-trained ASR model is largely tuned towards the source-domain, hurting the performance of target-domain models in vanilla transfer-learning. On the other hand, the encoder layers of the well-trained ASR model mostly capture the acoustic characteristics. We, therefore, propose to use the embeddings tapped from these encoder layers as features for a downstream Conformer target-domain model and show that they provide significant improvements. We do ablation studies on which encoder layer is optimal to tap the embeddings, as well as the effect of freezing or updating the well-trained ASR model's encoder layers. We further show that applying Spectral Augmentation (SpecAug) on the proposed features (this is in addition to default

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keysukhadia2022domain

Related papers

• A Domain Adaptation Framework For Speech Recognition Systems With Only Synthetic Data (2025)5.24
• A Simple Baseline For Domain Adaptation In End To End ASR Systems Using Synthetic Data (2022)7.16
• Updating Only Encoders Prevents Catastrophic Forgetting Of End-to-end ASR Models (2022)5.24
• Automatic Data Augmentation For Domain Adapted Fine-tuning Of Self-supervised Speech Representations (2023)0.00
• Residual Adapters For Parameter-efficient ASR Adaptation To Atypical And Accented Speech (2021)10.74
• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
• Pretraining By Backtranslation For End-to-end ASR In Low-resource Settings (2018)0.00
• Domain Robust Feature Extraction For Rapid Low Resource ASR Development (2018)7.50