The effect of pauses in dysarthric speech recognition study on Thai cerebral palsy children

Abstract

Dysarthric speech recognition (DSR) is continuously developed to improve the quality of life of people with speech impairment. This study aimed to investigate the effect of pauses in DSR. Speech corpus consists of 40 words including two subsets, (i) 20 bisyllabic words with specific design in order to contain all types of final consonant-initial consonant junction in Thai language and (ii) 20 monosyllabic words, which have some phoneme similar to that of the previous subset. Four cerebral palsy children with dysarthria and two normal children were participated. DSR was trained by using Hidden Markov Models (HMMs) in 3 approaches: phoneme-based (PSR), word-based (WSR), and pause reducing word-based (PRWSR). For the third approach, the pauses in words were automatically detected and reduced. The accuracy for PRWSR was compared with that of WSR by varying the duration of remaining pauses in PRWSR. Speech samples from the normal children were also recognized for comparing the accuracy. The results showed that PSR provided the highest recognition rate. The recognition rates of WSR and PRWSR are not significantly different but PRWSR grants a bit higher recognition rate than WSR. Comparing the remaining pause duration, 100 ms remaining pause duration is better than any other duration.

Communication System for Persons with Cerebral Palsy

“…They also frequently present difficulties in making gestures that prevent the production of written language with either pen or keyboard. No two patients are affected in the same way, including as for their intellectual abilities: despite mental retardation is frequent, many patients have a normal intelligence [6] [12]), speech recognition system [11], brain-computer interface [13] (Please note that optical motion tracking is not considered in this study, due to the uncontrolled movements of many people with cerebral palsy). The time required for text entry using virtual keyboards is important for people with cerebral palsy; more, such devices require a significant physical effort over a long period (see an example of a study in [3]).…”

“…The physical aids have the drawback that they must be used since childhood to be very effective [3]. Speech recognition is not yet effective for people suffering from dysarthria [11]. Brain-Computer Interfaces are not usable for complex tasks.…”

Proposition of a communication system used in mobility by users with physical disabilities, focus on cerebral palsy with athetoid problems

“…Speech recognition for users with CP [16]: voice recognition system is adapted to recognize how people with CP speak. The recognition algorithm retrieves the voice of people with disabilities into the wave, then normalizes it to get as close as possible to a wave of the voice of a person without a disability.…”

Comment communiquer lorsqu'on est un utilisateur infirme moteur cérébral (IMC) de type athétosique ? Étude de cas des différents moyens de communication

“…La reconnaissance vocale pour les IMC proposée par [13] est destinée aux personnes ayant une dysarthrie. Les chercheurs ont trouvé un algorithme permettant de transformer les ondes de la voix des personnes handicapées en ondes normalisées.…”