Automatic Speech Assessment For People With Aphasia Using Tdnn-Blstm With Multi-Task Learning
Keywords
Aphasia; Multi-task learning; Speech assessment; TDNN-BLSTM
Abstract
This paper describes an investigation on automatic speech assessment for people with aphasia (PWA) using a DNN based automatic speech recognition (ASR) system. The main problems being addressed are the lack of training speech in the intended application domain and the relevant degradation of ASR performance for impaired speech of PWA. We adopt the TDNN-BLSTM structure for acoustic modeling and apply the technique of multi-task learning with large amount of domain-mismatched data. This leads to a significant improvement on the recognition accuracy, as compared with a conventional single-task learning DNN system. To facilitate the extraction of robust text features for quantifying language impairment in PWA speech, we propose to incorporate N-best hypotheses and confusion network representation of the ASR output. The severity of impairment is predicted from text features and supra-segmental duration features using different regression models. Experimental results show a high correlation of 0.842 between the predicted severity level and the subjective Aphasia Quotient score.
Publication Date
1-1-2018
Publication Title
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume
2018-September
Number of Pages
3418-3422
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.21437/Interspeech.2018-1630
Copyright Status
Unknown
Socpus ID
85054969032 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85054969032
STARS Citation
Qin, Ying; Lee, Tan; Feng, Siyuan; and Hin Kong, Anthony Pak, "Automatic Speech Assessment For People With Aphasia Using Tdnn-Blstm With Multi-Task Learning" (2018). Scopus Export 2015-2019. 10040.
https://stars.library.ucf.edu/scopus2015/10040