Wei-Rong Chen
Cards
About
Titles
Associate Research Scientist in the Child Study Center
Biography
My research focuses on addressing linguistic issues in phonetics and phonology by using computational approaches and experimental methods, such as electromagnetic articulometry (EMA), ultrasound, laryngoscopy, palatography, etc. In Chen, Whalen & Tiede (2021)[Journal of Phonetics], I used a series of statistical models and a large articulatory dataset to establish a dual mechanism for intrinsic F0. My area of expertise also involves machine learning, deep neural networks, artificial intelligence (AI), and digital signal processing. I am the developer of DeepEdge (an AI tool based on convolutional neural network models and analytical algorithms for automatic tracking regions of interests in ultrasound video) (github.com/WeirongChen/DeepEdge) and ALPHUS (a 3D model of ultrasound probe stabilization system)(github.com/WeirongChen/ALPHUS).
KEY RESEARCH INTERESTS & EXPERTISE
Phonetics, articulatory phonology, speech science, computational linguistics, machine learning, artificial intelligence, computational \& statistical model, pathological speech
PROFESSIONAL APPOINTMENTS
2023-present: Associate Research Scientist (faculty). Yale University
2017-2023: Research Scientist. Haskins Laboratories
2016-2017: Postdoctoral fellow. Haskins Laboratories
Appointments
Child Study Center
Associate Research ScientistPrimary
Other Departments & Organizations
Education & Training
- PhD
- National Tsing Hua University, Linguistics (2015)
Research
Publications
Featured Publications
A dual mechanism for intrinsic f0
Chen W, Whalen D, Tiede M. A dual mechanism for intrinsic f0. Journal Of Phonetics 2021, 87: 101063. PMID: 34012182, PMCID: PMC8128133, DOI: 10.1016/j.wocn.2021.101063.Peer-Reviewed Original ResearchVowel coarticulation: Landmark statistics measure vowel aggressiona)
Chen W, Chang Y, Iskarous K. Vowel coarticulation: Landmark statistics measure vowel aggressiona). The Journal Of The Acoustical Society Of America 2015, 138: 1221-1232. PMID: 26328735, DOI: 10.1121/1.4928307.Peer-Reviewed Original ResearchSpatially Conditioned Speech Timing: Evidence and Implications
Shaw J, Chen W. Spatially Conditioned Speech Timing: Evidence and Implications. Frontiers In Psychology 2019, 10: 2726. PMID: 31866911, PMCID: PMC6906199, DOI: 10.3389/fpsyg.2019.02726.Peer-Reviewed Original ResearchVariability and Central Tendencies in Speech Production
Whalen D, Chen W. Variability and Central Tendencies in Speech Production. Frontiers In Communication 2019, 4: 49. DOI: 10.3389/fcomm.2019.00049.Peer-Reviewed Original ResearchF0-induced formant measurement errors result in biased variabilities
Chen WR, Whalen DH, Shadle CH. F0-induced formant measurement errors result in biased variabilities. The Journal Of The Acoustical Society Of America 2019, 145: el360-el366. PMID: 31153348, PMCID: PMC6909981, DOI: 10.1121/1.5103195.Peer-Reviewed Original ResearchVariability of articulator positions and formants across nine English vowels
Whalen DH, Chen WR, Tiede MK, Nam H. Variability of articulator positions and formants across nine English vowels. Journal Of Phonetics 2018, 68: 1-14. PMID: 30034052, PMCID: PMC6053058, DOI: 10.1016/j.wocn.2018.01.003.Peer-Reviewed Original Research
2024
Assessing ultrasound probe stabilization for quantifying speech production contrasts using the Adjustable Laboratory Probe Holder for UltraSound (ALPHUS)
Chen W, Stern M, Whalen D, Derrick D, Carignan C, Best C, Tiede M. Assessing ultrasound probe stabilization for quantifying speech production contrasts using the Adjustable Laboratory Probe Holder for UltraSound (ALPHUS). Journal Of Phonetics 2024, 105: 101339. DOI: 10.1016/j.wocn.2024.101339.Peer-Reviewed Original ResearchThe [s -- > ʃ] sound change in /str-/ contexts: how temporal changes in the acoustic spectrum affect fricative percept
Shadle C, Koenig L, Chen W. The [s -- > ʃ] sound change in /str-/ contexts: how temporal changes in the acoustic spectrum affect fricative percept. The Journal Of The Acoustical Society Of America 2024, 155: a315-a315. DOI: 10.1121/10.0027641.Peer-Reviewed Original ResearchAssessing accuracy of resonances obtained with reassigned spectrograms from the “ground truth” of physical vocal tract models
Shadle C, Fulop S, Chen W, Whalen D. Assessing accuracy of resonances obtained with reassigned spectrograms from the “ground truth” of physical vocal tract models. The Journal Of The Acoustical Society Of America 2024, 155: 1253-1263. PMID: 38341748, PMCID: PMC10858790, DOI: 10.1121/10.0024548.Peer-Reviewed Original Research
2023
Refining and extending measures for fricative spectra, with special attention to the high-frequency rangea)
Shadle C, Chen W, Koenig L, Preston J. Refining and extending measures for fricative spectra, with special attention to the high-frequency rangea). The Journal Of The Acoustical Society Of America 2023, 154: 1932-1944. PMID: 37768114, PMCID: PMC10540850, DOI: 10.1121/10.0021075.Peer-Reviewed Original Research
Links & Media
Media
Motion-compensated ultrasound video for tongue movements
This image demonstrates a combination of ultrasound and electromagnetic articulography (EMA) for tracking the tongue movements during speech production. The ultrasound transducer (probe) was stabilized with a 3D-printed headset, and the head/probe movements were tracked and corrected by using EMA. Full video can be watched on YouTube: www.youtube.com/watch?v=5SWMKchYbBs