Year: 2025
Type: dissertation
Abstract: This study examines challenges Japanese learners face in learning oral English, focusing on prosody analysis from STEAC course data.Also, Generative Spoken Language Model (GSLM), sequence-to-sequence (seq-to-seq) Voice Conversion (VC), and Text-to-Speech (TTS) models were employed to analyze and predict student performance.Results show all models effectively forecast mimicry abilities, with proposed scenarios for optimal application, supporting tailored learning resources for diverse student needs.1. Bilabial 2. Labiodental 3. Interdental 4. Alveolar 5. Palatal 6. Velar 7. Uvular 8. Glottal.
Author: CHENG, Xiai
Institution: The University of Tokyo
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W7208020631