scispace - formally typeset
Search or ask a question
Topic

Dysarthria

About: Dysarthria is a research topic. Over the lifetime, 2402 publications have been published within this topic receiving 56554 citations.


Papers
More filters
Proceedings ArticleDOI
15 Sep 2019
TL;DR: This paper trains personalized models that achieve 62% and 35% relative WER improvement on these two groups of non-standard speech: speech from people with amyotrophic lateral sclerosis and accented speech, and shows that 71% of the improvement comes from only 5 minutes of training data.
Abstract: Automatic speech recognition (ASR) systems have dramatically improved over the last few years. ASR systems are most often trained from 'typical' speech, which means that underrepresented groups don't experience the same level of improvement. In this paper, we present and evaluate finetuning techniques to improve ASR for users with non-standard speech. We focus on two types of non-standard speech: speech from people with amyotrophic lateral sclerosis (ALS) and accented speech. We train personalized models that achieve 62% and 35% relative WER improvement on these two groups, bringing the absolute WER for ALS speakers, on a test set of message bank phrases, down to 10% for mild dysarthria and 20% for more serious dysarthria. We show that 71% of the improvement comes from only 5 minutes of training data. Finetuning a particular subset of layers (with many fewer parameters) often gives better results than finetuning the entire model. This is the first step towards building state of the art ASR models for dysarthric speech.

76 citations

Journal ArticleDOI
TL;DR: Although the statistics of vocal tract movement do not appear to be transferable between regular and disabled speakers, transforming the space of the former given knowledge of the latter before retraining gives high accuracy.
Abstract: Disabled speech is not compatible with modern generative and acoustic-only models of speech recognition (ASR). This work considers the use of theoretical and empirical knowledge of the vocal tract for atypical speech in labeling segmented and unsegmented sequences. These combined models are compared against discriminative models such as neural networks, support vector machines, and conditional random fields. Results show significant improvements in accuracy over the baseline through the use of production knowledge. Furthermore, although the statistics of vocal tract movement do not appear to be transferable between regular and disabled speakers, transforming the space of the former given knowledge of the latter before retraining gives high accuracy. This work may be applied within components of assistive software for speakers with dysarthria.

75 citations

Journal ArticleDOI
TL;DR: In this paper, the World Health Organization's International Classification of Functioning, Disability and Health (ICF) conceptual framework was used to examine the impact of dysarthria on speech intelligibility.
Abstract: Regardless of the underlying neuromotor impairment, an almost universal consequence of dysarthria is a reduction in speech intelligibility. The purpose of this article is to examine critically and to discuss issues related directly to speech intelligibility in speakers with dysarthria. Reduced speech intelligibility resulting from dysarthria is examined using the World Health Organization's International Classification of Functioning, Disability and Health (ICF) conceptual framework. We propose that the ICF conceptual framework facilitates an awareness of the multidimensional nature of disablement. Furthermore, the ICF facilitates a broad understanding of the complex nature of dysarthria, ranging from the neuroanatomical and physiological substrates contributing to reduced speech intelligibility, to the effects of this type of communication disorder on an individual's functioning in society and beyond. Finally, a case example is presented that describes how the ICF can be applied to an individual with dysarthria and reduced speech intelligibility.

75 citations

Journal ArticleDOI
TL;DR: This is the first software with the characteristics described above, and it is considered that it will help other researchers to contribute to the state-of-the-art in pathological speech assessment from different perspectives, e.g., from the clinical point of view for interpretation, and from the computer science point of views enabling the test of different measures and pattern recognition techniques.

75 citations

Journal ArticleDOI
TL;DR: Most respondents reported both speech and language symptoms, and many experienced restricted communicative participation, and the amount and type of speech-language pathology services received by people with PD was inadequate.
Abstract: Background Changes in communicative functions are common in Parkinson's disease (PD), but there are only limited data provided by individuals with PD on how these changes are perceived, what their consequences are, and what type of intervention is provided. Aim To present self-reported information about speech and communication, the impact on communicative participation, and the amount and type of speech-language pathology services received by people with PD. Methods Respondents with PD recruited via the Swedish Parkinson's Disease Society filled out a questionnaire accessed via a Web link or provided in a paper version. Results Of 188 respondents, 92.5% reported at least one symptom related to communication; the most common symptoms were weak voice, word-finding difficulties, imprecise articulation, and getting off topic in conversation. The speech and communication problems resulted in restricted communicative participation for between a quarter and a third of the respondents, and their speech caused embarrassment sometimes or more often to more than half. Forty-five percent of the respondents had received speech-language pathology services. Conclusions Most respondents reported both speech and language symptoms, and many experienced restricted communicative participation. Access to speech-language pathology services is still inadequate. Services should also address cognitive/linguistic aspects to meet the needs of people with PD.

75 citations


Network Information
Related Topics (5)
Parkinson's disease
27.9K papers, 1.1M citations
82% related
Multiple sclerosis
26.8K papers, 886.7K citations
77% related
White matter
14.8K papers, 782.7K citations
77% related
Cerebellum
16.8K papers, 794K citations
76% related
Traumatic brain injury
25.7K papers, 793.7K citations
76% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023229
2022415
2021164
2020138
2019125
201888