Hugging Face Trending Papers June 4, 2026

GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech

Read the original on Hugging Face Trending Papers →

We propose GLASS, a framework for composable acoustic style control in zero-shot autoregressive text-to-speech (TTS) that learns controls from post-generation rewards rather than style labels. In zero-shot TTS, a speaker prompt often entangles speaker identity with prosodic attributes such as speaking rate and pitch, making it difficult to change style without changing the prompt itself.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 26

VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation

arXiv:2606. 26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.

By Tianxin Xie, Chenxing Li, Dong Yu, Li Liu

diffusion reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Sep 24

Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech

The paper introduces GUARD, a lightweight speaker identity unlearning framework designed to prevent re-identification in zero-shot text-to-speech systems. GUARD employs a learned speaker gate and speaker-agnostic activation steering on a frozen TTS backbone, optimizing steering vectors through group-relative reward optimization to reduce similarity to forgotten speakers while maintaining intelligibility and naturalness. Experiments on CosyVoice2 show that GUARD significantly lowers forget-speaker similarity and re-identification accuracy while preserving the ability to reproduce retained speakers.

By Hyoeun Kim, Yujun Lee, Kyuhong Shim

multimodal

arXiv AI

Jun 3

FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

arXiv:2606. 02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition.

By Haolong Zheng, Siyin Wang, Xulin Fan, Zengrui Jin, Mark Hasegawa-Johnson

llms reinforcement-learning multimodal

arXiv AI

Sep 1

FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations

arXiv:2606.02615v2 Announce Type: replace-cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognit...

By Haolong Zheng, Siyin Wang, Xulin Fan, Zengrui Jin, Mark Hasegawa-Johnson

llms reinforcement-learning multimodal

Hugging Face Trending Papers

Jun 17

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings. These systems operate within speech-only pipelines that produce clean vocal sequences without the ambient texture of real conversations.

rag benchmarks

arXiv AI

Jun 18

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.

By Michael Finkelson, Daniel Segal, Eitan Richardson, Shahar Armon, Nani Goldring, Poriya Panet, Nir Zabari, Benjamin Brazowski, Or Patashnik, Yoav HaCohen

rag benchmarks

One email a morning, machine-written

Related stories

VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation

Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech

FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors

Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors