4 papers
Rethinking Discrete Speech Representation Tokens for Accent Generation
Jinzuomu Zhong, Yi Wang, Korin Richmond +1
Discrete Speech Representation Tokens (DSRTs) have become a foundational component in speech generation. While prior work has extensively studied phonetic and speaker information i…
Pairwise Evaluation of Accent Similarity in Speech Synthesis
Jinzuomu Zhong, Suyuan Liu, Dan Wells +1
Despite growing interest in generating high-fidelity accents, evaluating accent similarity in speech synthesis has been underexplored. We aim to enhance both subjective and objecti…
AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
Jinzuomu Zhong, Korin Richmond, Zhiba Su +1
While recent Zero-Shot Text-to-Speech (ZS-TTS) models have achieved high naturalness and speaker similarity, they fall short in accent fidelity and control. To address this issue,…
Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning
Siqi Sun, Korin Richmond
Recent work has shown the feasibility and benefit of bootstrapping an integrated sequence-to-sequence (Seq2Seq) linguistic frontend from a traditional pipeline-based frontend for t…