A Study Of Enhancement, Augmentation, And Autoencoder Methods For Domain Adaptation In Distant Speech Recognition

Abstract

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem, leaving little effort to adapting close-talking speech recognizers to distant speech. In this work, we review several approaches from a domain adaptation perspective. These approaches, including speech enhancement, multi-condition training, data augmentation, and autoencoders, all involve a transformation of the data between domains. We conduct experiments on the AMI data set, where these approaches can be realized under the same controlled setting. These approaches lead to different amounts of improvement under their respective assumptions. The purpose of this paper is to quantify and characterize the performance gap between the two domains, setting up the basis for studying adaptation of speech recognizers from close-talking speech to distant speech.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keytang2018a

Related papers

• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23
• Autoencoder Based Domain Adaptation For Speaker Recognition Under Insufficient Channel Information (2017)10.07
• 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
• Unsupervised Domain Adaptation By Adversarial Learning For Robust Speech Recognition (2018)0.00
• Contaminated Speech Training Methods For Robust DNN-HMM Distant Speech Recognition (2017)4.52
• Deep Learning For Distant Speech Recognition (2017)0.00
• Data Augmentation Methods For End-to-end Speech Recognition On Distant-talk Scenarios (2021)6.34