Cover Image

No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shin, Seungyoun, Ahn, Dongha, Kim, Jiwoo, Jeon, Sungwook
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Artificial Intelligence Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
by: Liu, Jiaxuan, et al.
Published: (2024)

Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody
by: Yoon, Jinsung, et al.
Published: (2025)

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting
by: Han, Wooseok, et al.
Published: (2024)

ProKWS: Personalized Keyword Spotting via Collaborative Learning of Phonemes and Prosody
by: Pan, Jianan, et al.
Published: (2026)

Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
by: Zhong, Jinzuomu, et al.
Published: (2023)

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
by: Lee, Kyowoon, et al.
Published: (2025)

DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
by: Oh, Hyung-Seok, et al.
Published: (2023)

A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer
by: Maurya, Himanshu, et al.
Published: (2024)

Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition
by: Chevi, Rendi, et al.
Published: (2024)

Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning
by: Goel, Arnav, et al.
Published: (2024)

Benchmarking Prosody Encoding in Discrete Speech Tokens
by: Onda, Kentaro, et al.
Published: (2025)

KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness
by: Kim, Jinyoung, et al.
Published: (2026)

LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learning
by: Dhar, Sandipan, et al.
Published: (2025)

Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning
by: Zhao, Junchuan, et al.
Published: (2025)

CrossVoice: Crosslingual Prosody Preserving Cascade-S2ST using Transfer Learning
by: Hira, Medha, et al.
Published: (2024)

Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech
by: Borodin, Kirill, et al.
Published: (2025)

ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis
by: He, Xiangheng, et al.
Published: (2024)

Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS
by: Borodin, Kirill, et al.
Published: (2026)

Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?
by: Tsiamas, Ioannis, et al.
Published: (2024)

A2TTS: TTS for Low Resource Indian Languages
by: Bhadoriya, Ayush Singh, et al.
Published: (2025)

Usefulness of Emotional Prosody in Neural Machine Translation
by: Brazier, Charles, et al.
Published: (2024)

RepeaTTS: Towards Feature Discovery through Repeated Fine-Tuning
by: Sigurgeirsson, Atli, et al.
Published: (2025)

FluentEditor2: Text-based Speech Editing by Modeling Multi-Scale Acoustic and Prosody Consistency
by: Liu, Rui, et al.
Published: (2024)

ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs
by: Eren, Eray, et al.
Published: (2025)

From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling
by: Cao, Yifei, et al.
Published: (2025)

Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM
by: Cui, Wenqian, et al.
Published: (2026)

TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
by: Bataev, Vladimir, et al.
Published: (2025)

Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling
by: Karapiperis, Sotirios, et al.
Published: (2024)

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
by: Chou, Cheng-Kang, et al.
Published: (2025)

Expressive Prompting: Improving Emotion Intensity and Speaker Consistency in Zero-Shot TTS
by: Wang, Haoyu, et al.
Published: (2024)

Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition
by: Ma, Ziyang, et al.
Published: (2023)

Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling
by: Jiang, Yuepeng, et al.
Published: (2024)

Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation
by: Jeon, Yejin, et al.
Published: (2024)

Differentiable Reward Optimization for LLM based TTS system
by: Gao, Changfeng, et al.
Published: (2025)

Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID
by: Handoyo, Ahmad Alfani, et al.
Published: (2024)

Prosody-Driven Privacy-Preserving Dementia Detection
by: Woszczyk, Dominika, et al.
Published: (2024)

Prosody Analysis of Audiobooks
by: Pethe, Charuta, et al.
Published: (2023)

Controllable Prosody Generation With Partial Inputs
by: Iliescu, Dan Andrei, et al.
Published: (2023)

Prosody Labeling with Phoneme-BERT and Speech Foundation Models
by: Koriyama, Tomoki
Published: (2025)

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
by: Zhou, Siyi, et al.
Published: (2025)