eess.ASNov 9, 2026

REAL: Reward Modeling through Evidence-Linked Analysis of Lifelikeness in Generated Speech

Authors: Yaodong Song, Jie Lian, Xusheng Yang, Genliang Zhao, Hongjie Chen, Jian Kang, Zhen-Hua Ling, Jie Li, 

Organizations: University of Science and Technology of China, Hefei · Xingchen AGI Lab, China Telecom Artificial Intelligence Technology Co., Ltd.

Abstract

As modern text-to-speech systems become increasingly intelligible and natural, evaluation is shifting from detecting gross synthesis failures to identifying subtle departures from lifelike human delivery. Because large-scale listening tests are costly and slow, speech reward models can serve as scalable automatic judges for comparing generated utterances, curating data, and supporting iterative TTS development. Existing speech reward models can predict scores or pairwise preferences and may generate natural-language rationales, but their supervision is typically defined at the utterance or pair level. The connection between local acoustic phenomena and the final preference therefore remains implicit. We introduce REAL, a framework for Reward modeling through Evidence-linked Analysis of Lifelikeness in generated speech. Its central idea is to supervise not only the final pairwise preference but also a structured account of its supporting observations, linking local audio spans to perceptual phenomena, affected dimensions, and the overall judgment. Specifically, REAL-Jury constructs these evidence-linked reports through timestamp alignment, multi-model analysis, and dispute-oriented deliberation. REAL-Judge learns to generate them from paired audio inputs. REAL-Eval assesses preference prediction in two tiers, from salient perceptual differences to subtle distinctions among strong TTS systems. Instantiated with MiMo-Audio, REAL-Judge improves pairwise preference accuracy over its backbone by 16.01 and 11.41 percentage points on the two tiers, respectively, and outperforms the open-source speech reward models SpeechJudge and UniSRM on both tiers.

Figures & tables

Explore similar work

CardsList
  1. UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment

    May 22, 2026Yuanyuan Wang, Dongchao Yang, Yayue Deng +4Reward ModelingSpeech Generation Evaluation

  2. Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation

    Sep 1, 2026Thibaut Thonet, Jos Rozen, Laurent BesacierLLM AlignmentTTS Evaluation