PulseAugur
EN
LIVE 10:10:35

WordVoice framework offers explicit, multi-dimensional control for LLM-based TTS

By PulseAugur Editorial · [2 sources] ·

Researchers have introduced WordVoice, a novel framework designed to enhance control over Large Language Model (LLM)-based Text-to-Speech (TTS) systems. This system addresses the limitations of current implicit generation methods by enabling explicit, multi-dimensional word-level acoustic manipulation. To support this, a substantial bilingual dataset named WordVoice-5A, featuring five dimensions of word-level annotations, was created. The WordVoice framework incorporates a bound-token mechanism for acoustic planning and a fine-grained modulation module to bridge the gap between discrete tokens and continuous waveforms, offering superior control while maintaining synthesis stability. AI

IMPACT Enhances control over LLM-based TTS systems, potentially improving applications like audiobook narration and video dubbing.

RANK_REASON The cluster contains a research paper detailing a new framework and dataset for TTS.

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

WordVoice framework offers explicit, multi-dimensional control for LLM-based TTS

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Sihang Nie, Jinxin Ji, Xiaofen Xing, Deyi Tuo, Chengbin Jin, Jialong Mai, Xiangmin Xu ·

    WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS

    arXiv:2607.06461v1 Announce Type: cross Abstract: While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenario…

  2. arXiv cs.CL TIER_1 English(EN) · Xiangmin Xu ·

    WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS

    While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit end-to-end generation paradigms, resulting in coarse-grained control. In scenarios demanding precise stylistic interventions and st…

RELATED ENTITIES

RELATED TOPICS