← Search

Myeonghun Jeong

2 accepted papers

2025

Evidential-TTS: High Fidelity Zero-Shot Text-to-Speech Using Evidential Deep Learning

ICASSP 2025accepted

We propose Evidential-TTS, a novel zero-shot text-to-speech (TTS) system based on evidential deep learning (EDL). The model includes a length regulator to ensure precise alignment between phonemes and acoustic tokens. This module allows the evidential token generator to convert the aligned phoneme s…

Cited by 0SourceScholar
2023

Improving Learning Objectives for Speaker Verification from the Perspective of Score Comparison

ICASSP 2023accepted

Deep speaker embedding systems are usually trained with classification-based or end-to-end learning objectives. Popular end-to-end approaches utilize deep metric learning, which can be viewed as a few-shot classification objective. In this paper, we investigate the limit of conventional learning obj…

Cited by 0SourceScholar