AI News HubLIVE
原文

Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models

This paper proposes novel techniques for inter-utterance style interpolation and intra-utterance style transition in prompt-based TTS models, addressing limitations of coarse global control. Methods include direction vector interpolation and KV-cache swapping with sliding-window attention masking. Experiments show high success rates in gender conversion and smooth style transitions within utterances.

Article intelligence

EngineersAdvanced

Key points

  • Inter-utterance interpolation via direction vectors between contrastive style prompts enables smooth transitions.
  • Intra-utterance transition uses KV-cache swapping and sliding-window masking to overcome attention bias.
  • Achieves 99-100% gender conversion success, up to 36 Hz pitch variation, and up to 1.6 syllables/second speed change.
  • Intra-utterance method maintains speaker similarity of 0.81-0.91 and perceptual smoothness scores of 3.48-4.48.

Why it matters

This matters because inter-utterance interpolation via direction vectors between contrastive style prompts enables smooth transitions.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.27376] Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models

[Submitted on 9 Apr 2026]

Title:Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models

View a PDF of the paper titled Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models, by Jaehoon Kang and 3 other authors

View PDF HTML (experimental)

Abstract:While prompt-based text-to-speech (TTS) models enable natural language-driven speaking style control, they often provide limited fine-grained control and apply a single global style across an utterance. This restricts practical use cases that require continuous style attribute interpolation across utterances and time-varying style transitions within a single utterance. In this paper, we propose novel techniques to achieve both capabilities in existing prompt-based TTS models. For inter-utterance style interpolation, we compute direction vectors between contrastive style prompts in the embedding space and perform simple interpolation, enabling smooth transitions between style characteristics. For intra-utterance style transition, we first identify a strong attention bias toward early tokens in autoregressive TTS decoders, causing the initial audio realization to dominate subsequent generation. To mitigate this effect, we introduce KV-cache swapping and sliding-window attention masking. Experiments demonstrate that our proposed inter-utterance interpolation achieves a 99-100% success rate in gender conversion, up to 36 Hz pitch variation, and up to 1.6 syllables-per-second speed change. Our intra-utterance transition maintains a speaker similarity of 0.81-0.91 and achieves perceptual smoothness scores of 3.48-4.48.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.27376 [cs.CL]

(or arXiv:2605.27376v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.27376

arXiv-issued DOI via DataCite

Submission history

From: Jaehoon Kang [view email] [v1] Thu, 9 Apr 2026 01:06:26 UTC (1,394 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Unlocking Fine-Grained and Within-Utterance Speaking Style Control in Prompt-Based Text-to-Speech Models, by Jaehoon Kang and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)