speech biomarker

use speech as a biomarker for clinical diagnosis

Since 2021, I have been worked as a graduate research assistant on an [NSF-funded project] (https://www.nsf.gov/awardsearch/showAward?AWD_ID=2037266) led by Ratree Wayland and Kevin Tang. The project aims to integrate deep learning models with articulatory and acoustic data to predict the degrees of lenition in various speech types. This innovative approach seeks to provide unique diagnostics for both medical and linguistic purposes.

To quantify the degree of lenition, we employed a deep learning Phonet model. This model is trained to calculate the posterior probabilities of sonorant and continuant features of Spanish stops in diverse contexts, allowing us to compare these measurements with previously established metrics of lenition, such as those reported by Broś et al. (2021) and Kingston (2008).

Related Publications

2023

  1. LAN
    Quantitative acoustic versus deep learning metrics of lenition
    Ratree Wayland, Kevin Tang, Fenqi Wang, Sophia Vellozzi, and Rahul Sengupta
    Languages, 2023
    HTML
  2. JASA
    From sonority hierarchy to posterior probability as a measure of lenition: The case of Spanish stops
    Kevin Tang, Ratree Wayland, Fenqi Wang, Sophia Vellozzi, Rahul Sengupta, and Lori Altman
    The Journal of the Acoustical Society of America, 2023
    HTML
  3. ICPhS
    Measuring gradient effects of alcohol on speech with neural networks’ posterior probability of phonological features (accepted)
    Ratree Wayland, Kevin Tang, Sophia Vellozzi, Fenqi Wang, and Rahul Sengupta
    In Proceedings of the 20th International Congress of the Phonetic Sciences, 2023
  4. POMA
    Neural networks’ posterior probability as measure of effects of alcohol on speech
    Ratree Wayland, Kevin Tang, Fenqi Wang, Sophia Vellozzi, and Rahul Sengupta
    In Proceedings of Meetings on Acoustics, 2023
    HTML
  5. POMA
    Lenition measures: Neural networks’ posterior probability versus acoustic cues
    Ratree Wayland, Kevin Tang, Fenqi Wang, Sophia Vellozzi, and Rahul Sengupta
    In Proceedings of Meetings on Acoustics, 2023
    HTML
  6. ASA
    Neural networks’ posterior probability as measure of effects of alcohol on speech
    Ratree Wayland, Kevin Tang, Fenqi Wang, Sophia Vellozzi, and Rahul Sengupta
    In The 184th Meeting of Acoustical Society of America, 2023

2022

  1. ASA
    Lenition measures: Neural networks’ posterior probability versus acoustic cues
    Ratree Wayland, Kevin Tang, Fenqi Wang, Sophia Vellozzi, Rahul Sengupta, and Lori Altman
    In The 183rd Meeting of Acoustical Society of America, 2022
    HTML
  2. ASA
    Measuring second language acquisition of spanish lenition
    Rachel Meyer, Ratree Wayland, and Fenqi Wang
    In The 183rd Meeting of Acoustical Society of America, 2022
    HTML