论文题目：MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition
作者：Jiaming Zhou (Nankai University)*; Shiwan Zhao (Independent Researcher); Ning Jiang (Mashang Consumer Finance Co., Ltd.); Guoqing Zhao (Mashang Consumer Finance Co., Ltd); Yong Qin (Nankai University)
通讯作者：Yong Qin (Nankai University)
录用会议：ICASSP 2023
论文链接：https://ieeexplore.ieee.org/abstract/document/10095177/
论文概述：End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain by transferring knowledge from the source to the target domain. To improve transferability, existing UDA approaches mainly focus on matching the distributions of the source and target domains globally and/or locally, while ignoring the model discriminability. In this paper, we propose a novel UDA approach for ASR via inter-domain MAtching and intra-domain DIscrimination (MADI), which improves
the model transferability by fine-grained inter-domain matching and discriminability by intra-domain contrastive discrimination simultaneously. Evaluations on the Libri-Adapt dataset demonstrate the effectiveness of our approach. MADI reduces the relative word error rate (WER) on cross-device and cross-environment ASR by 17.7% and 22.8%, respectively.
