Machine Learning Based Assistive Speech Technology for People with Neurological Disorders

Chandrakala, S.

doi:10.1007/978-3-030-30817-9_6

Cited by 2 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive work has been conducted to advance algorithms for speech recognition. Automatic Speech Recognition consists of machine recognition of audio patterns and transcribing speech to text [8]. While text-to-speech has been extensively investigated [5], multiple recognition errors still occur when users interact with speech interfaces [1,17,28,29], hindering the experience of the users.…”

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

“…Such impairment is characterized by breathy voice, stuffy speech, and imprecise articulation. The work contributes with a model feature learning approach with a discriminative classifier, which showed better performance than state-of-the-art solutions using hidden Markov Models [8].…”

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

“…Concerning neurological disorders and speech impairments due to limited motor control, Chandrakala (2019) studied the application of machine learning algorithms in voice recognition for users with dysarthric (partial) speech [8,31,52]. Such impairment is characterized by breathy voice, stuffy speech, and imprecise articulation.…”

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

“…Moreover, it is one of the most efficient forms of interpersonal communication [4]. Thanks to the advances in automatic speech recognition, speech has been increasingly adopted as an interaction modality for smart home devices, navigation systems, and intelligent personal assistants [5][6][7][8]. The proper use of automatic speech recognition enables users to quickly access information and resources, control utilities and appliances, and request and acquire services through voice commands in a handsfree way.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Limitations in Speech Recognition for Young Adults with Down Syndrome

Cibrian,

Chen,

Anderson

et al. 2024

Preprint

View full text Add to dashboard Cite

Speech recognition has the potential to make technology more accessible to users. However, the accuracy of speech recognition remains limited for users with disabilities, including those with Down Syndrome, and the types and frequencies of recognition errors are poorly understood. This paper characterizes these problems, focusing on errors occurring when recognizing Down Syndrome speech. We analyze the transcripts from six speech recognition algorithms (Google, IBM, Otter.ai, Microsoft, AssemblyAI, OpenAI) using the audio content of 15 individuals with Down Syndrome (331 dialogues; 3,428 words). Our analysis shows (1) significant difference in speech recognition accuracy for people with Down Syndrome compared to neurotypical users; (2) the best algorithm for recognizing Down Syndrome speech is OpenAI (Word Accuracy = 67\%; F1-score = 0.944), and (3) there is a prevalence of deletion errors followed by substitutions and insertions. These findings have implications for enhancing speech recognition for the next-generation voice assistants to meet the needs of users with Down Syndrome.

show abstract

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

Section: Automatic Speech Recognition For Users With Diverse Needsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Limitations in Speech Recognition for Young Adults with Down Syndrome

Cibrian,

Chen,

Anderson

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Patients with chronic neurodegenerative diseases (e.g., Alzheimer, Parkinson, amyotrophic lateral sclerosis), demyelinating diseases as multiple sclerosis, and persons with acquired brain injuries (e.g., stroke, post-coma) have been impacted by lockdowns—making them vulnerable during the COVID-19 ( 16 ). In order to deal with these issues, one may envisage assistive technology (AT)-based strategies ( 17 , 18 ).…”

Section: Introductionmentioning

confidence: 99%

Virtual Reality as a Technological-Aided Solution to Support Communication in Persons With Neurodegenerative Diseases and Acquired Brain Injury During COVID-19 Pandemic

Stasolla

Matamala-Gomez

Bernini³

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

The COVID-19 poses an ongoing threat to lives around the world and challenges the existing public health and medical service delivery. The lockdown or quarantine measures adopted to prevent the spread of COVID-19 has caused the interruption in ongoing care and access to medical care including to patients with existing neurological conditions. Besides the passivity, isolation, and withdrawal, patients with neurodegenerative diseases experience difficulties in communication due to a limited access to leisure opportunities and interaction with friends and relatives. The communication difficulties may exacerbate the burden on the caregivers. Therefore, assistive-technologies may be a useful strategy in mitigating challenges associated with remote communication. The current paper presents an overview of the use of assistive technologies using virtual reality and virtual body ownership in providing communication opportunities to isolated patients, during COVID-19, with neurological diseases and moderate-to-severe communication difficulties. We postulate that the assistive technologies-based intervention may improve social interactions in patients with neurodegenerative diseases and acquired brain injury-thereby reducing isolation and improving their quality of life and mental well-being.

show abstract

Machine Learning Based Assistive Speech Technology for People with Neurological Disorders

Cited by 2 publications

References 34 publications

Limitations in Speech Recognition for Young Adults with Down Syndrome

Limitations in Speech Recognition for Young Adults with Down Syndrome

Virtual Reality as a Technological-Aided Solution to Support Communication in Persons With Neurodegenerative Diseases and Acquired Brain Injury During COVID-19 Pandemic

Contact Info

Product

Resources

About