Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yao, Jixun, Yang, Yuguang, Pan, Yu, Feng, Yuan, Ning, Ziqian, Ye, Jianhao, Zhou, Hongbin, Xie, Lei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909975592304640
author Yao, Jixun
Yang, Yuguang
Pan, Yu
Feng, Yuan
Ning, Ziqian
Ye, Jianhao
Zhou, Hongbin
Xie, Lei
author_facet Yao, Jixun
Yang, Yuguang
Pan, Yu
Feng, Yuan
Ning, Ziqian
Ye, Jianhao
Zhou, Hongbin
Xie, Lei
contents Integrating human feedback to align text-to-speech (TTS) system outputs with human preferences has proven to be an effective approach for enhancing the robustness of language model-based TTS systems. Current approaches primarily focus on using preference data annotated at the utterance level. However, frequent issues that affect the listening experience often only arise in specific segments of audio samples, while other segments are well-generated. In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems. FPO focuses on addressing localized issues in generated samples rather than uniformly optimizing the entire utterance. Specifically, we first analyze the types of issues in generated samples, categorize them into two groups, and propose a selective training loss strategy to optimize preferences based on fine-grained labels for each issue type. Experimental results show that FPO enhances the robustness of zero-shot TTS systems by effectively addressing local issues, significantly reducing the bad case ratio, and improving intelligibility. Furthermore, FPO exhibits superior data efficiency compared with baseline systems, achieving similar performance with fewer training samples.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02950
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
Yao, Jixun
Yang, Yuguang
Pan, Yu
Feng, Yuan
Ning, Ziqian
Ye, Jianhao
Zhou, Hongbin
Xie, Lei
Audio and Speech Processing
Sound
Integrating human feedback to align text-to-speech (TTS) system outputs with human preferences has proven to be an effective approach for enhancing the robustness of language model-based TTS systems. Current approaches primarily focus on using preference data annotated at the utterance level. However, frequent issues that affect the listening experience often only arise in specific segments of audio samples, while other segments are well-generated. In this study, we propose a fine-grained preference optimization approach (FPO) to enhance the robustness of TTS systems. FPO focuses on addressing localized issues in generated samples rather than uniformly optimizing the entire utterance. Specifically, we first analyze the types of issues in generated samples, categorize them into two groups, and propose a selective training loss strategy to optimize preferences based on fine-grained labels for each issue type. Experimental results show that FPO enhances the robustness of zero-shot TTS systems by effectively addressing local issues, significantly reducing the bad case ratio, and improving intelligibility. Furthermore, FPO exhibits superior data efficiency compared with baseline systems, achieving similar performance with fewer training samples.
title Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2502.02950