Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES

Abstract: 

Aphasia is a type of acquired language impairment resulting from brain injury. Speech assessment is an important part of the comprehensive assessment process for aphasic patients. It is based on the acoustical and linguistic analysis of patients’ speech elicited through pre-defined story-telling tasks. This type of narrative spontaneous speech embodies multi-fold atypical characteristics related to the underlying language impairment. This paper presents an investigation on automatic speech assessment for Cantonese-speaking aphasic patients using an automatic speech recognition (ASR) system. A novel approach to extracting robust text features from erroneous ASR output is developed based on word embedding methods. The text features can effectively distinguish the stories told by an impaired speaker from those by unimpaired ones. On the other hand, a set of supra-segmental duration features are derived from syllable-level time alignments produced by the ASR system, to characterize the atypical prosody of impaired speech. The proposed text features, duration features and their combination are evaluated in a binary classification experiment as well as in automatic prediction of subjective assessment score. The results clearly show that the text features are very effective in the intended task of aphasia assessment, while using duration features could provide additional benefit.

up
0 users have voted:

Paper Details

Authors:
Tan Lee, Anthony Pak Hin Kong
Submitted On:
12 April 2018 - 11:52pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Ying Qin
Document Year:
2018
Cite

Document Files

poster_QinYing_ICASSP2018_final.pdf

(46 downloads)

Subscribe

[1] Tan Lee, Anthony Pak Hin Kong, "AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2571. Accessed: Jul. 16, 2018.
@article{2571-18,
url = {http://sigport.org/2571},
author = {Tan Lee; Anthony Pak Hin Kong },
publisher = {IEEE SigPort},
title = {AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES},
year = {2018} }
TY - EJOUR
T1 - AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES
AU - Tan Lee; Anthony Pak Hin Kong
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2571
ER -
Tan Lee, Anthony Pak Hin Kong. (2018). AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES. IEEE SigPort. http://sigport.org/2571
Tan Lee, Anthony Pak Hin Kong, 2018. AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES. Available at: http://sigport.org/2571.
Tan Lee, Anthony Pak Hin Kong. (2018). "AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES." Web.
1. Tan Lee, Anthony Pak Hin Kong. AUTOMATIC SPEECH ASSESSMENT FOR APHASIC PATIENTS BASED ON SYLLABLE-LEVEL EMBEDDING AND SUPRA-SEGMENTAL DURATION FEATURES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2571