The sophistication of artificial intelligence (AI) technologies has significantly advanced in the past decade. However, the observed unpredictability and variability of AI behavior in noisy signals is still underexplored and represents a challenge when trying to generalize AI behavior to real-life environments, especially for people with a speech disorder, who already experience reduced speech intelligibility. In the context of developing assistive technology for people with Parkinson's disease using automatic speech recognition (ASR), this pilot study reports on the performance of Google Cloud speech-to-text technology with dysarthric and healthy speech in the presence of multi-talker babble noise at different intensity levels. Despite sensitivities and shortcomings, it is possible to control the performance of these systems with current tools in order to measure speech intelligibility in real-life conditions.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8727902 | PMC |
| http://dx.doi.org/10.3389/frai.2021.809321 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Improving Cognitive Empathy Through Traumatic Brain Injury Experiential Learning: A Novel Mixed Methods Approach for Speech-Language Pathology Graduate Education.
Am J Speech Lang Pathol
January 2025
Good Samaritan Medical Center Foundation, Lafayette, CO.
Purpose: The aim of this study was to gauge the impacts of cognitive empathy training experiential learning on traumatic brain injury (TBI) knowledge, awareness, confidence, and empathy in a pilot study of speech-language pathology graduate students.
Method: A descriptive quasi-experimental convergent parallel mixed methods design intervention pilot study (QUAL + QUANT) was conducted with a diverse convenience sample of 19 first- and second-year speech-language pathology graduate students who engaged in a half-day TBI point-of-view simulation. The simulation was co-constructed through a participatory design with those living with TBI based on Kolb's experiential learning model and followed the recommendations for point-of-view simulation ethics.
Synchronous Analysis of Speech Production and Lips Movement to Detect Parkinson's Disease Using Deep Learning Methods.
Diagnostics (Basel)
December 2024
GITA Lab., Faculty of Engineering, University of Antioquia, Medellín 050010, Colombia.
Background/objectives: Parkinson's disease (PD) affects more than 6 million people worldwide. Its accurate diagnosis and monitoring are key factors to reduce its economic burden. Typical approaches consider either speech signals or video recordings of the face to automatically model abnormal patterns in PD patients.
View Article and Find Full Text PDFEffect of the Levels and Sources of Noise on the Sleep Quality of Conscious Patients in Emergency Intensive Care Unit.
Noise Health
January 2025
Department of EICU, Wenzhou Central Hospital; The Dingli Clinical College of Wenzhou Medical University, Wenzhou, Zhejiang Province, China.
Purpose: This study aimed to assess the levels and sources of noise in the emergency intensive care unit (EICU) of an emergency department and investigate their effects on the sleep quality of conscious patients.
Methods: A study was conducted on patients admitted to the EICU from December 2020 to December 2023. They were categorised according to their sleep quality with the Pittsburgh Sleep Quality Index.
Using voice recognition and machine learning techniques for detecting patient-reported outcomes from conversational voice in palliative care patients.
Jpn J Nurs Sci
January 2025
Department of Palliative Nursing, Health Sciences, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan.
Aim: Patient-reported outcome measures (PROMs) are increasingly used in palliative care to evaluate patients' symptoms and conditions. Healthcare providers often collect PROMs through conversations. However, the manual entry of these data into electronic medical records can be burdensome for healthcare providers.
View Article and Find Full Text PDFMultilingual Prediction of Cognitive Impairment with Large Language Models and Speech Analysis.
Brain Sci
December 2024
School of Biomedical Engineering, Science and Health Systems, Drexel University, Philadelphia, PA 19104, USA.
Background: Cognitive impairment poses a significant global health challenge, emphasizing the critical need for early detection and intervention. Traditional diagnostics like neuroimaging and clinical evaluations are often subjective, costly, and inaccessible, especially in resource-poor settings. Previous research has focused on speech analysis primarily conducted using English data, leaving multilingual settings unexplored.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!