MSU Expert: How AI Can Help People Understand Research and Increase Trust in Science
Michigan State UniversityMSU expert: How AI can help people understand research and increase trust in science
MSU expert: How AI can help people understand research and increase trust in science
Bo偶ena Kostek from Gda艅sk University of Technology is exploring how speech-to-text programs can be better used in the medical field. By studying how clear speech affects STT accuracy, she hopes to improve its usefulness for health care professionals. A detailed audio dataset was created with Polish medical terms spoken by doctors and specialists in areas like cardiology and pulmonology. This dataset was analyzed using an Automatic Speech Recognition model for transcription, and several metrics were used to evaluate the quality of the speech recognition.
The Speech Accessibility Project has two new partners 鈥 The Matthew Foundation and the Massachusetts Down Syndrome Congress 鈥 as it continues to recruit adults with Down syndrome who live in the United States and Canada. The project also allows residents of Puerto Rico to participate.
University of Miami researchers find a link between early vocabulary composition and later language development in children with cochlear implants.
In the Journal of the Acoustical Society of America, an interdisciplinary team explored possible regularities in vocal emotional expressions by comparing expressive interjections, such as 鈥渨ow,鈥 to nonlinguistic vocalizations, such as screams and cries, from across the globe. The researchers analyzed vowels in interjections from 131 languages, comparing them with nearly 500 vowels from vocalizations produced in joyful, painful, or disgusting contexts. Each of the three emotions yielded consistent and distinct vowel signatures across cultures in vocalizations.
Linguistics and computer science researchers at Tufts University have discovered some of the root causes of the inability of AI to engage in human-like conversation
Electronics and Telecommunications Research Institute (ETRI) is conducting research on the development of an AI technology that can evaluate and predict brain function degeneration and brain-related diseases such as mild cognitive impairment, dementia, etc., by analyzing the speech utterances of the elderly that can be obtained through their daily conversations.
Chulalongkorn University, through its Institute of Asian Studies, Indian Studies Center, and the Faculty of Arts, hosted the 鈥淧hipitbharat 2024鈥 teacher training program to enhance knowledge of both traditional and modern India.
For children who are undergoing evaluation for surgery to treat epilepsy at Children鈥檚 Hospital Los Angeles, the Wada test, also known as the intracarotid amobarbital procedure, can be an important step in the process. During this test, doctors put certain areas of the brain to sleep to help pinpoint which areas correspond to the patient鈥檚 language and memory.
A team of researchers, including psycholinguist Jutta Mueller from the University of Vienna, has discovered that newborns are capable of learning complex sound sequences that follow language-like rules. This groundbreaking study provides long-sought evidence that the ability to perceive dependencies between non-adjacent acoustic signals is innate.
The Speech Accessibility Project is now recruiting Canadian adults with Parkinson鈥檚 disease, cerebral palsy, amyotrophic lateral sclerosis, Down syndrome and those who have had a stroke.
An expert on aging, disappearing languages and migration 鈥 and a self-taught polyglot, too 鈥 the academic has joined UdeM鈥檚 Department of Demography as a professor.
Researchers at UCLA Health and the University of North Carolina Frank Porter Graham Child Development Institute (FPG) will co-lead a unique project to assess behavioral and neurological markers of language development in low-income children within their family settings, gathering valuable information that could lead to earlier, more targeted interventions for a population that has been largely underrepresented in autism research.
Listening to people with Parkinson鈥檚 disease made an automatic speech recognizer 30% more accurate, according to initial findings from the Speech Accessibility Project. Speech recordings used in the study are freely available to organizations looking to improve their voice recognition devices.
Using immersive virtual reality (i-VR) 鈥 a technology where, through use of a headset and controllers, a user can navigate myriad virtual environments 鈥 researchers at the University of South Australia have created engineering-specific scenarios where students can practice their engineering skills, using language that is specific to the job.
Public speaking may be one of the most crucial skills for politicians, playing a vital role in their ability to connect with voters and colleagues. But after being diagnosed with a rare brain disorder a year ago, Virginia Representative, Jennifer Wexton, literally lost her voice.
A brain-computer interface developed by UC Davis Health accurately translates brain signals into speech. The device implanted in the brain of a man with ALS is the most accurate system of its kind.
For media seeking commentary for back-to-school stories and other education coverage, FSU faculty will participate in a virtual media briefing Aug. 6. Faculty with expertise in literacy and language development, school psychology and counseling, autism and intellectual disability, and mathematics education will be available to answer questions.