Search

Your search keyword '"Wang, Xianhui"' showing total 999 results
Start Over Author "Wang, Xianhui"
999 results on '"Wang, Xianhui"'

4. Individualized Conditioning and Negative Distances for Speaker Separation

Author

Sun, Tao, Abuhajar, Nidal, Gong, Shuyu, Wang, Zhewei, Smith, Charles D., Wang, Xianhui, Xu, Li, and Liu, Jundong

Subjects
Computer Science - Sound, Computer Science - Artificial Intelligence, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Speaker separation aims to extract multiple voices from a mixed signal. In this paper, we propose two speaker-aware designs to improve the existing speaker separation solutions. The first model is a speaker conditioning network that integrates speech samples to generate individualized speaker conditions, which then provide informed guidance for a separation module to produce well-separated outputs. The second design aims to reduce non-target voices in the separated speech. To this end, we propose negative distances to penalize the appearance of any non-target voice in the channel outputs, and positive distances to drive the separated voices closer to the clean targets. We explore two different setups, weighted-sum and triplet-like, to integrate these two distances to form a combined auxiliary loss for the separation networks. Experiments conducted on LibriMix demonstrate the effectiveness of our proposed models., Comment: Accepted to ICMLA 2022

Published
2022

28. Supporting Youth with Autism Learning Social Competence: A Comparison of Game- and Nongame-Based Activities in 3D Virtual World

Author

Wang, Xianhui and Xing, Wanli

Abstract

This study explored youth with Autism Spectrum Disorder (ASD) learning social competence in the context of innovative 3D virtual learning environment and the effects of gaming as a central element of the learning experience. The empirical study retrospectively compared the social interactions of 11 adolescents with ASD in game-and nongame-based 3D collaborative learning activities in the same social competence training curriculum. We employed a learning analytics approach - association rule mining to uncover the associative rules of verbal social interaction and nonverbal social interaction contributors from the large dataset of the coded social behaviors. By comparing the rules across the game and nongame activities, we found a significant difference in youth with ASD's social performance. The results of the group comparison study indicated that the co-occurrence of verbal and nonverbal behaviors is much stronger in the game-based learning activities. The game activities also yielded more diverse social interaction behavior patterns. On the other hand, in the nongame activities, students' social interaction behavior patterns are much more limited. Furthermore, the impact of game design principles on learning is then discussed in this paper.

Published
2022
Full Text
View/download PDF

31. A Systematic Review of Expressive and Receptive Prosody in People with Dementia

Author

Oh, Chorong, Morris, Richard J., and Wang, Xianhui

Abstract

Purpose: This review was designed to provide a systematic overview of prosody in people with a primary diagnosis of dementia (PwD) and evaluate the potential use of prosodic features for diagnosis of dementia. Method: A systematic search of five databases was conducted using Medical Subject Headings and keywords. Studies included in the review were evaluated for their methodological quality using the modified Joanna Briggs Institute checklist. Results: A total of 14 articles were identified as being relevant for this review. Among the 14 articles, the methodological quality ranged, with eight rated as weak, four rated as moderate, and two rated as strong. Ten of the 14 articles had people with Alzheimer's disease (AD) as participants, and the remaining four had people with frontotemporal dementia as participants. Four articles focused on receptive prosody, another six focused on expressive prosody, and the remaining four articles were investigations into both. The 14 articles presented inconsistent findings, and various tasks were used to measure prosodic features in PwD in the articles. Prosody was studied as a diagnostic tool for dementia in four of the articles, all of which were based on expressive prosody in individuals with AD. Among the four articles, three proposed the use of automatic speech analysis for diagnosis of AD. Conclusions: This review demonstrates that prosody in PwD is an underinvestigated area. In particular, it was concerning that most articles were of weak methodological quality. Nevertheless, it was found that prosody may be a potential diagnostic tool for assessing dementia. More studies that replicate the existing studies and those with stronger methodology are needed to confirm that receptive and/or expressive prosody can be used for dementia diagnosis.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results