Extending unsupervised phonetic segmentation with self-supervised speech embeddings
Poster presented at the 190th Meeting of the Acoustical Society of America
A Praat script for unsupervised phoneme segmentation based on spectro-temporal representation
Poster presented at the 189th Meeting of the Acoustical Society of America
(code available here, proceedings paper here)
Overfitting in deep learning models for disfluency detection in bilingual children
(joint work with Caryn Iwakiri, Pei-Tzu Tsai, and Janet Bang)
Poster presented at the 2025 American Speech and Hearing Association (ASHA) Convention
(designated as an ASHA Convention Centennial Session)
Understanding AI model development and application in disfluency detection
(joint work with Caryn Iwakiri, Pei-Tzu Tsai, and Janet Bang)
Poster presented at the 2025 American Speech and Hearing Association (ASHA) Convention
Unsupervised phoneme segmentation using a transformer autoencoder
Poster presented at BayPhon2025@UCSC
(code available here)