@techreport{oai:ipsj.ixsq.nii.ac.jp:00231272,
 author = {Yuqin, Lin and Longbiao, Wang and Jianwu, Dang and Nobuaki, Minematsu and Yuqin, Lin and Longbiao, Wang and Jianwu, Dang and Nobuaki, Minematsu},
 issue = {14},
 month = {Nov},
 note = {Addressing dysarthric speech variability in Automatic Speech Recognition (ASR) is crucial for improving human-computer interactions for everyone. This paper proposes the Auxiliary Features Fusion (AFFusion) module, which leverages phonetic and articulatory-related features from models like wav2vec to compensate for distorted acoustics in dysarthric ASR. Experimental results using AFFusion with various feature models demonstrate its effectiveness on dysarthric databases. Interestingly, the analysis suggests that AFFusion shares similarities with human speech perception processes, offering potential insights into addressing fuzzy recognition in dysarthric ASR based on the motor theory of speech perception., Addressing dysarthric speech variability in Automatic Speech Recognition (ASR) is crucial for improving human-computer interactions for everyone. This paper proposes the Auxiliary Features Fusion (AFFusion) module, which leverages phonetic and articulatory-related features from models like wav2vec to compensate for distorted acoustics in dysarthric ASR. Experimental results using AFFusion with various feature models demonstrate its effectiveness on dysarthric databases. Interestingly, the analysis suggests that AFFusion shares similarities with human speech perception processes, offering potential insights into addressing fuzzy recognition in dysarthric ASR based on the motor theory of speech perception.},
 title = {Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models},
 year = {2023}
}