Journal ArticleDOI
Formant modification to improve intelligibility of dysarthric speech
TLDR
The aim of this study is to understand the effects which formant frequencies have on the intelligibility of speech and to enhance the vowel region of the dysarthric speech, based on the modification of formants through linear predictive coding (LPC) analysis.Abstract:
Dysarthria is a motor speech disorder, characterised by poor articulation, resulting in speech which is slurred, slow and difficult to understand. The aim of this study is to understand the effects which formant frequencies have on the intelligibility of speech and to enhance the vowel region of the dysarthric speech, based on the modification of formants through linear predictive coding (LPC) analysis. The formants of the dysarthric speech are modified such that they closely match the normal target formants, without much variation in the pitch. The method adopted for formant modification retains the characteristics and naturalness of the speaker.read more
References
More filters
Book
Discrete-Time Speech Signal Processing: Principles and Practice
TL;DR: This chapter discusses the Discrete-Time Speech Signal Processing Framework, a model based on the FBS Method, and its applications in Speech Communication Pathway and Homomorphic Signal Processing.
Journal ArticleDOI
Improving the intelligibility of dysarthric speech
Alexander Kain,John-Paul Hosom,Xiaochuan Niu,Jan P. H. van Santen,Melanie Fried-Oken,Janice Staehely +5 more
TL;DR: This study significantly improved the intelligibility of dysarthric vowels of one speaker from 48% to 54%, as evaluated by a vowel identification task using 64 CVC stimuli judged by 24 listeners.
Formant re-synthesis of dysarthric speech.
TL;DR: Results indicate that the transformation step enhances intelligibility, and that removal of vocal fry enhances perceived quality, however, the initial step of stylizing the formant trajectories results in a decrement inelligibility, thereby reducing the net impact of the process.
Journal ArticleDOI
Word identification testing in the diagnostic evaluation of dysarthric speech
TL;DR: In this article, a method for the clinical assessment of segmental contrastivity in dysarthric speech is presented, based on listeners' identifications of single words spoken by the examined subjects.
Proceedings ArticleDOI
Analysis and Synthesis of Vowels Using Matlab
TL;DR: A software environment in Matlab is proposed, in order to extract the main features from the Romanian vowels and to synthesize the vowels.