Exploring the influence of general and specific factors on the recognition accuracy of an ASR system for dysarthric speaker

Mustafa, Mumtaz Begum; Rosdi, Fadhilah; Salim, Siti Salwah; Mughal, Muhammad Umair

doi:10.1016/j.eswa.2015.01.033

Cited by 29 publications

(13 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the aphasic multi-types (i.e., Global aphasia, Broca’s aphasia, Wernicke’s aphasia and Amnesic aphasia) speech datasets are scarce and often have a small sample for each severity level group [ 10 ]. This finding agrees with what was reported in the literature where data scarcity [ 39 ], abnormal speech patterns [ 40 ], and speaker variability [ 41 ] are challenging to any classification problem.…”

Section: Discussionsupporting

confidence: 92%

Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment

Mahmoud

Kumar

et al. 2021

Sensors

View full text Add to dashboard Cite

Speech assessment is an essential part of the rehabilitation procedure for patients with aphasia (PWA). It is a comprehensive and time-consuming process that aims to discriminate between healthy individuals and aphasic patients, determine the type of aphasia syndrome, and determine the patients’ impairment severity levels (these are referred to here as aphasia assessment tasks). Hence, the automation of aphasia assessment tasks is essential. In this study, the performance of three automatic speech assessment models based on the speech dataset-type was investigated. Three types of datasets were used: healthy subjects’ dataset, aphasic patients’ dataset, and a combination of healthy and aphasic datasets. Two machine learning (ML)-based frameworks, classical machine learning (CML) and deep neural network (DNN), were considered in the design of the proposed speech assessment models. In this paper, the DNN-based framework was based on a convolutional neural network (CNN). Direct or indirect transformation of these models to achieve the aphasia assessment tasks was investigated. Comparative performance results for each of the speech assessment models showed that quadrature-based high-resolution time-frequency images with a CNN framework outperformed all the CML frameworks over the three dataset-types. The CNN-based framework reported an accuracy of 99.23 ± 0.003% with the healthy individuals’ dataset and 67.78 ± 0.047% with the aphasic patients’ dataset. Moreover, direct or transformed relationships between the proposed speech assessment models and the aphasia assessment tasks are attainable, given a suitable dataset-type, a reasonably sized dataset, and appropriate decision logic in the ML framework.

show abstract

Section: Discussionsupporting

confidence: 92%

Performance Evaluation of Machine Learning Frameworks for Aphasia Assessment

Mahmoud

Kumar

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…There has been extensive work in the related field of dysarthric speech recognition [9][10][11][12][13][14][15]. ASR for dysarthric and disordered speech in general is faced with abnormal speech patterns, high speaker variability [16], and data scarcity [11]. Methods for alleviating these problems include speaker-dependent GMM adaptation [9,11,12], generation of auxiliary acoustic features used within tandem-based systems [10,14], learning speakerspecific pronunciation [13], and speaker selection [15].…”

Section: Asr For Disordered Speechmentioning

confidence: 99%

Improving Automatic Recognition of Aphasic Speech with AphasiaBank

Provost

2016

Interspeech 2016

View full text Add to dashboard Cite

Automatic recognition of aphasic speech is challenging due to various speech-language impairments associated with aphasia as well as a scarcity of training data appropriate for this speaker population. AphasiaBank, a shared database of multimedia interactions primarily used by clinicians to study aphasia, offers a promising source of data for Deep Neural Network acoustic modeling. In this paper, we establish the first large-vocabulary continuous speech recognition baseline on AphasiaBank and study recognition accuracy as a function of diagnoses. We investigate several out-of-domain adaptation methods and show that AphasiaBank data can be leveraged to significantly improve the recognition rate on a smaller aphasic speech corpus. This work helps broaden the understanding of aphasic speech recognition, demonstrates the potential of AphasiaBank, and guides researchers who wish to use this database for their own work.

show abstract

“…In the same line of research, Caballero-Morales and Trujillo-Romero (2014) improved the recognition rates for dysarthric patients by integrating multiple pronunciation patterns in an expert system using genetic algorithms. Later on, Mustafa, Rosdi, Salim, and Mughal (2015) provided a thorough analysis of general and specific factors that affect the recognition accuracy of that system and previous ones. …”

Section: Diagnosismentioning

confidence: 99%