Add BrightSurf on Google Email

Automatic speech recognition learned to understand people with Parkinson’s disease — by listening to them

Researchers trained an automatic speech recognizer on recordings from people with dysarthria related to Parkinson's disease, achieving a 30% accuracy improvement. The study, led by Mark Hasegawa-Johnson, provides valuable data for improving voice recognition devices.

SourceBeckman Institute for Advanced Science and Technology·JournalJournal of Speech Language and Hearing Research·TypeComputational simulation/modeling·DateSep 27, 2024

Brain recordings capture musicality of speech — with help from Pink Floyd

Neuroscientists at UC Berkeley have successfully reconstructed a recognizable song from brain recordings, capturing the electrical activity of brain regions tuned to music attributes. This breakthrough could enable future brain implants with prosodic content, improving communication for patients with speech disorders.

SourceUniversity of California - Berkeley·JournalPLOS Biology·TypeExperimental study·DateAug 15, 2023

Can conventional speech therapy combined with singing address voice problems in individuals with Parkinson’s disease?

A new study found that combining conventional speech therapy with singing can improve voice problems in individuals with Parkinson's disease. The tele-rehabilitation program showed significant improvements in voice intensity and Voice Handicap Index scores, suggesting a more effective treatment approach.

SourceWiley·JournalInternational Journal of Language & Communication Disorders·DateJun 7, 2023

Crowdsourcing can help researchers assess efficacy of Parkinson’s treatment, research finds

Researchers found that crowdsourced listeners can accurately assess voice quality for people with Parkinson's disease, supporting the use of crowdsourcing to evaluate speech samples. The study replicated a previous finding that intensive voice and articulation therapies improve voice quality.

SourceNew York University·JournalJournal of Speech Language and Hearing Research·TypeExperimental study·DateApr 16, 2023

To identify a voice, brains rely on sight

A new study suggests that the brain's ability to identify a voice is linked to its ability to recognize faces, with a common brain center processing both visual and auditory information. This finding has important implications for understanding disorders where voice or face recognition is compromised.

SourceUniversity of Pittsburgh·JournalJournal of Neurophysiology·DateJan 3, 2023

The invention of Lithuanian scientists – AI will become an assistant in voice analysis

Researchers from Kaunas University of Technology and Lithuanian University of Health Sciences developed an AI-based system to evaluate the 'substitute voice' of laryngectomy patients, allowing for faster detection of pathologies. The Acoustic Substitution Voice Index (ASVI) uses acoustic parameters and artificial intelligence methods t...

SourceKaunas University of Technology·JournalApplied Sciences·TypeComputational simulation/modeling·DateNov 29, 2022

More than 60 percent of teachers have voice problems

A study by researchers at the University of Malaga found that 62.7% of early childhood and primary education teachers suffer from voice disorders on a daily or weekly basis. The study highlights the psychosocial dimensions associated with these disorders, including less social support, role conflict, and reduced respect for their work.

SourceSpanish Foundation for Science and Technology·JournalFolia Phoniatrica et Logopaedica·DateMay 19, 2010