PulseAugur
EN
LIVE 06:48:16

UltraVoice dataset enhances speech style control in dialogue models

By PulseAugur Editorial · [1 sources] ·

Researchers have introduced UltraVoice, a large-scale dataset designed to improve fine-grained speech style control in spoken dialogue models. The dataset includes over 830 hours of speech dialogues with instructions across six stylistic dimensions: emotion, speed, volume, accent, language, and composite styles. Fine-tuning models like SLAM-Omni and VocalNet on UltraVoice has shown significant improvements in stylistic controllability and instruction following, without compromising core conversational abilities. The dataset's utility also extends to training controllable Text-to-Speech models. AI

IMPACT Enhances human-like interaction in spoken dialogue systems and improves controllable Text-to-Speech models.

RANK_REASON The cluster contains an academic paper detailing a new dataset and methodology for speech synthesis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

UltraVoice dataset enhances speech style control in dialogue models

How we ranked this

Signal score
27 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains an academic paper detailing a new dataset and methodology for speech synthesis. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Wenming Tu, Guanrou Yang, Ruiqi Yan, Wenxi Chen, Ziyang Ma, Yipeng Kang, Kai Yu, Xie Chen, Zilong Zheng ·

    UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models

    arXiv:2510.22588v2 Announce Type: replace-cross Abstract: Spoken dialogue models currently lack the ability for fine-grained speech style control, a critical capability for human-like interaction that is often overlooked in favor of purely functional capabilities like reasoning a…

RELATED ENTITIES

RELATED TOPICS