Saved in:
Bibliographic Details
Main Authors: Yang, Qing, Liu, Zhenghao, Du, Yangfan, Huang, Pengcheng, Xiao, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14628
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914449918525440
author Yang, Qing
Liu, Zhenghao
Du, Yangfan
Huang, Pengcheng
Xiao, Tong
author_facet Yang, Qing
Liu, Zhenghao
Du, Yangfan
Huang, Pengcheng
Xiao, Tong
contents Recent advances in Text-To-Speech (TTS) synthesis have achieved near-human speech quality in neutral speaking styles. However, most existing approaches either depend on costly emotion annotations or optimize surrogate objectives that fail to adequately capture perceptual emotional quality. As a result, the generated speech, while semantically accurate, often lacks expressive and emotionally rich characteristics. To address these limitations, we propose RLAIF-SPA, a novel framework that integrates Reinforcement Learning from AI Feedback (RLAIF) to directly optimize both emotional expressiveness and intelligibility without human supervision. Specifically, RLAIF-SPA incorporates Automatic Speech Recognition (ASR) to provide semantic accuracy feedback, while leveraging structured reward modeling to evaluate prosodic-emotional consistency. RLAIF-SPA enables more precise and nuanced control over expressive speech generation along four structured evaluation dimensions: Structure, Emotion, Speed, and Tone. Extensive experiments on Libri-Speech, MELD, and Mandarin ESD datasets demonstrate consistent gains across clean read speech, conversational dialogue, and emotional speech. On Libri-Speech, RLAIF-SPA consistently outperforms Chat-TTS, achieving a 26.1% reduction in word error rate, a 9.1% improvement in SIM-O, and over 10% gains in human subjective evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14628
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
Yang, Qing
Liu, Zhenghao
Du, Yangfan
Huang, Pengcheng
Xiao, Tong
Computation and Language
Artificial Intelligence
Recent advances in Text-To-Speech (TTS) synthesis have achieved near-human speech quality in neutral speaking styles. However, most existing approaches either depend on costly emotion annotations or optimize surrogate objectives that fail to adequately capture perceptual emotional quality. As a result, the generated speech, while semantically accurate, often lacks expressive and emotionally rich characteristics. To address these limitations, we propose RLAIF-SPA, a novel framework that integrates Reinforcement Learning from AI Feedback (RLAIF) to directly optimize both emotional expressiveness and intelligibility without human supervision. Specifically, RLAIF-SPA incorporates Automatic Speech Recognition (ASR) to provide semantic accuracy feedback, while leveraging structured reward modeling to evaluate prosodic-emotional consistency. RLAIF-SPA enables more precise and nuanced control over expressive speech generation along four structured evaluation dimensions: Structure, Emotion, Speed, and Tone. Extensive experiments on Libri-Speech, MELD, and Mandarin ESD datasets demonstrate consistent gains across clean read speech, conversational dialogue, and emotional speech. On Libri-Speech, RLAIF-SPA consistently outperforms Chat-TTS, achieving a 26.1% reduction in word error rate, a 9.1% improvement in SIM-O, and over 10% gains in human subjective evaluations.
title RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.14628