Professional challenges in computer-assisted speech therapy

Popovici, Doru-Vlad; Buică-Belciu, Cristian

doi:10.1016/j.sbspro.2012.01.175

Cited by 16 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Waiting for speech deficiencies to decline by themselves may be proven hazardous and could result in poor communication skills, as well as damaged psychology and self-esteem. As Speech Therapy can sometimes be time-consuming and laborious for both therapists and patients, intelligent diagnosis and therapy systems have been created as a way to enhance language therapy efficiency [5].…”

Section: Icts In Assessment Proceduresmentioning

confidence: 99%

ICTs in Speech and Language Therapy

Drigas

Petrova

2014

Int. J. Eng. Ped.

View full text Add to dashboard Cite

Abstract-Over the past decade speech and language therapy has taken an interesting turn towards the use of information communication technologies (ICTs) for diagnosis of disorders and delivery of therapy. In many cases ICTs have worked as assistive tools to therapists, while in others as sole providers of therapy, especially in remote areas. In this report we provide a brief overview of the most representative articles for applications and assistive technologies used for assessment and intervention purposes in Speech Therapy according to the type of disorders.

show abstract

Section: Icts In Assessment Proceduresmentioning

confidence: 99%

ICTs in Speech and Language Therapy

Drigas

Petrova

2014

Int. J. Eng. Ped.

View full text Add to dashboard Cite

show abstract

“…According to the outcomes of the efficacy tests presented in [3], user satisfaction towards such a system appears to be quite high. However, most of these systems are not yet capable of automatically detecting problems at the level of individual speech sounds, which are known to have an impact on speech intelligibility [4][5][6][7][8]. Our goal is to develop robust automatic speech recognition (ASR) systems for pathological speech and incorporate the ASR technology to detect these problems.…”

Section: Introductionmentioning

confidence: 99%

Articulatory Features for ASR of Pathological Speech

et al. 2018

View full text Add to dashboard Cite

In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech. Despite long-lasting efforts to build speaker-and text-independent ASR systems for people with dysarthria, the performance of state-of-the-art systems is still considerably lower on this type of speech than on normal speech. The most prominent reason for the inferior performance is the high variability in pathological speech that is characterized by the spectrotemporal deviations caused by articulatory impairments due to various etiologies. To cope with this high variation, we propose to use speech representations which utilize articulatory information together with the acoustic properties. A designated acoustic model, namely a fused-featuremap convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time convolution on articulatory features is trained and tested on a Dutch and a Flemish pathological speech corpus. The ASR performance of fCNN-based ASR system using joint features is compared to other neural network architectures such conventional CNNs and time-frequency convolutional networks (TFCNNs) in several training scenarios.

show abstract

“…According to the outcomes of the efficacy tests presented in [9], user satisfaction towards such a system appears to be quite high. However, most of these systems are not yet capable of automatically detecting problems at the level of individual speech sounds, which are known to have an impact on speech intelligibility [10][11][12][13][14]. Our goal is to develop more robust acoustic models for pathological speech and incorporate automatic speech recognition (ASR) technology to detect these problems.…”

Section: Introductionmentioning

confidence: 99%

Multi-Stage DNN Training for Automatic Recognition of Dysarthric Speech

Yılmaz¹,

Ganzeboom²,

Cucchiarini³

et al. 2017

Interspeech 2017

View full text Add to dashboard Cite

Incorporating automatic speech recognition (ASR) in individualized speech training applications is becoming more viable thanks to the improved generalization capabilities of neural network-based acoustic models. The main problem in developing applications for dysarthric speech is the relative in-domain data scarcity. Collecting representative amounts of dysarthric speech data is difficult due to rigorous ethical and medical permission requirements, problems in accessing patients who are generally vulnerable and often subject to altering health conditions and, last but not least, the high variability in speech resulting from different pathological conditions. Developing such applications is even more challenging for languages which in general have fewer resources, fewer speakers and, consequently, also fewer patients than English, as in the case of a mid-sized language like Dutch. In this paper, we investigate a multi-stage deep neural network (DNN) training scheme aimed at obtaining better modeling of dysarthric speech by using only a small amount of in-domain training data. The results show that the system employing the proposed training scheme considerably improves the recognition of Dutch dysarthric speech compared to a baseline system with single-stage training only on a large amount of normal speech or a small amount of in-domain data.

show abstract

Professional challenges in computer-assisted speech therapy

Cited by 16 publications

References 10 publications

ICTs in Speech and Language Therapy

ICTs in Speech and Language Therapy

Articulatory Features for ASR of Pathological Speech

Multi-Stage DNN Training for Automatic Recognition of Dysarthric Speech

Contact Info

Product

Resources

About