Jun Wang1,2, Prasanna V Kothalkar1, Myungjong Kim1, Andrea Bandini3, Beiming Cao1, Yana Yunusova3, Thomas F Campbell2, Daragh Heitzman4, Jordan R Green5. 1. a Department of Bioengineering , Speech Disorders & Technology Lab. 2. b Callier Center for Communication Disorders, University of Texas at Dallas , Richardson , TX , USA. 3. c Department of Speech-Language Pathology , University of Toronto , Toronto , Canada. 4. d MDA/ALS Center , Texas , TX , USA. 5. e Department of Communication Sciences and Disorders , MGH Institute of Health Professions , Boston , MA , USA.
Abstract
Purpose: This research aimed to automatically predict intelligible speaking rate for individuals with Amyotrophic Lateral Sclerosis (ALS) based on speech acoustic and articulatory samples. Method: Twelve participants with ALS and two normal subjects produced a total of 1831 phrases. NDI Wave system was used to collect tongue and lip movement and acoustic data synchronously. A machine learning algorithm (i.e. support vector machine) was used to predict intelligible speaking rate (speech intelligibility × speaking rate) from acoustic and articulatory features of the recorded samples. Result: Acoustic, lip movement, and tongue movement information separately, yielded a R2 of 0.652, 0.660, and 0.678 and a Root Mean Squared Error (RMSE) of 41.096, 41.166, and 39.855 words per minute (WPM) between the predicted and actual values, respectively. Combining acoustic, lip and tongue information we obtained the highest R2 (0.712) and the lowest RMSE (37.562 WPM). Conclusion: The results revealed that our proposed analyses predicted the intelligible speaking rate of the participant with reasonably high accuracy by extracting the acoustic and/or articulatory features from one short speech sample. With further development, the analyses may be well-suited for clinical applications that require automatic speech severity prediction.
Purpose: This research aimed to automatically predict intelligible speaking rate for individuals with Amyotrophic Lateral Sclerosis (ALS) based on speech acoustic and articulatory samples. Method: Twelve participants with ALS and two normal subjects produced a total of 1831 phrases. NDI Wave system was used to collect tongue and lip movement and acoustic data synchronously. A machine learning algorithm (i.e. support vector machine) was used to predict intelligible speaking rate (speech intelligibility × speaking rate) from acoustic and articulatory features of the recorded samples. Result: Acoustic, lip movement, and tongue movement information separately, yielded a R2 of 0.652, 0.660, and 0.678 and a Root Mean Squared Error (RMSE) of 41.096, 41.166, and 39.855 words per minute (WPM) between the predicted and actual values, respectively. Combining acoustic, lip and tongue information we obtained the highest R2 (0.712) and the lowest RMSE (37.562 WPM). Conclusion: The results revealed that our proposed analyses predicted the intelligible speaking rate of the participant with reasonably high accuracy by extracting the acoustic and/or articulatory features from one short speech sample. With further development, the analyses may be well-suited for clinical applications that require automatic speech severity prediction.
Authors: Matthew C Kiernan; Steve Vucic; Benjamin C Cheah; Martin R Turner; Andrew Eisen; Orla Hardiman; James R Burrell; Margaret C Zoing Journal: Lancet Date: 2011-02-04 Impact factor: 79.321
Authors: Jordan R Green; Yana Yunusova; Mili S Kuruvilla; Jun Wang; Gary L Pattee; Lori Synhorst; Lorne Zinman; James D Berry Journal: Amyotroph Lateral Scler Frontotemporal Degener Date: 2013-07-30 Impact factor: 4.092
Authors: Panying Rong; Yana Yunusova; Jun Wang; Lorne Zinman; Gary L Pattee; James D Berry; Bridget Perry; Jordan R Green Journal: PLoS One Date: 2016-05-05 Impact factor: 3.240
Authors: Kaila L Stipancic; Kira M Palmer; Hannah P Rowe; Yana Yunusova; James D Berry; Jordan R Green Journal: J Speech Lang Hear Res Date: 2021-11-11 Impact factor: 2.674
Authors: Namita A Goyal; James D Berry; Anthony Windebank; Nathan P Staff; Nicholas J Maragakis; Leonard H van den Berg; Angela Genge; Robert Miller; Robert H Baloh; Ralph Kern; Yael Gothelf; Chaim Lebovits; Merit Cudkowicz Journal: Muscle Nerve Date: 2020-01-22 Impact factor: 3.217