Saved in:
Bibliographic Details
Main Authors: Wang, Yue, Ma, Ruotian, Chen, Xingyu, Shi, Zhengliang, Chen, Wanshun, Liu, Huang, Yao, Jiadi, Yang, Qu, Jiang, Qingxuan, Ye, Fanghua, Li, Juntao, Zhang, Min, Tu, Zhaopeng, Li, Xiaolong, Linus
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.26514
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912618500849664
author Wang, Yue
Ma, Ruotian
Chen, Xingyu
Shi, Zhengliang
Chen, Wanshun
Liu, Huang
Yao, Jiadi
Yang, Qu
Jiang, Qingxuan
Ye, Fanghua
Li, Juntao
Zhang, Min
Tu, Zhaopeng
Li, Xiaolong
Linus
author_facet Wang, Yue
Ma, Ruotian
Chen, Xingyu
Shi, Zhengliang
Chen, Wanshun
Liu, Huang
Yao, Jiadi
Yang, Qu
Jiang, Qingxuan
Ye, Fanghua
Li, Juntao
Zhang, Min
Tu, Zhaopeng
Li, Xiaolong
Linus
contents The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, typically failing to leverage their powerful instruction-following capabilities. This limitation hinders the model's ability to follow text instructions for controllable Text-to-Speech~(TTS). To address this, we propose a new paradigm inspired by ``operationalism'' that decouples instruction understanding from speech generation. We introduce BatonVoice, a framework where an LLM acts as a ``conductor'', understanding user instructions and generating a textual ``plan'' -- explicit vocal features (e.g., pitch, energy). A separate TTS model, the ``orchestra'', then generates the speech from these features. To realize this component, we develop BatonTTS, a TTS model trained specifically for this task. Our experiments demonstrate that BatonVoice achieves strong performance in controllable and emotional speech synthesis, outperforming strong open- and closed-source baselines. Notably, our approach enables remarkable zero-shot cross-lingual generalization, accurately applying feature control abilities to languages unseen during post-training. This demonstrates that objectifying speech into textual vocal features can more effectively unlock the linguistic intelligence of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26514
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
Wang, Yue
Ma, Ruotian
Chen, Xingyu
Shi, Zhengliang
Chen, Wanshun
Liu, Huang
Yao, Jiadi
Yang, Qu
Jiang, Qingxuan
Ye, Fanghua
Li, Juntao
Zhang, Min
Tu, Zhaopeng
Li, Xiaolong
Linus
Computation and Language
The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, typically failing to leverage their powerful instruction-following capabilities. This limitation hinders the model's ability to follow text instructions for controllable Text-to-Speech~(TTS). To address this, we propose a new paradigm inspired by ``operationalism'' that decouples instruction understanding from speech generation. We introduce BatonVoice, a framework where an LLM acts as a ``conductor'', understanding user instructions and generating a textual ``plan'' -- explicit vocal features (e.g., pitch, energy). A separate TTS model, the ``orchestra'', then generates the speech from these features. To realize this component, we develop BatonTTS, a TTS model trained specifically for this task. Our experiments demonstrate that BatonVoice achieves strong performance in controllable and emotional speech synthesis, outperforming strong open- and closed-source baselines. Notably, our approach enables remarkable zero-shot cross-lingual generalization, accurately applying feature control abilities to languages unseen during post-training. This demonstrates that objectifying speech into textual vocal features can more effectively unlock the linguistic intelligence of LLMs.
title BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
topic Computation and Language
url https://arxiv.org/abs/2509.26514