# Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Source: [Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability]() Collection index: [llms.txt]() Data updated: 2026-05-30T05:00:04.258Z Authors: Yong Ren, Jingbei Li, Haiyang Sun, Yujie Chen, Cheng Yi, Yechang Huang, Hao Gu, Ye Bai, Xuerui Yang Published: 2026-01-30T07:27:48.000Z ## Abstract Recent advances in Large Audio Language Models (LALMs) have extended Text-to-Speech (TTS) to interactive role-play scenarios, which demand high expressiveness and strict adherence to role-play instructions. However, existing models struggle to maintain stylistic consistency with character profiles and scene descriptions across multi-turn dialogues. A critical bottleneck is the lack of objective metrics for quantifying speaking style. To bridge this gap, we propose Mean Continuation Log-Probability (MCLP) as both an evaluation metric and a reward signal, validated on LALM-based Role-Play TTS (RP-TTS) tasks. MCLP leverages the in-context learning capability of pretrained LALMs to measure the likelihood of ground-truth speech tokens conditioned on a contextual history consisting of the transcript, generated speech, and repeated transcript, serving as a proxy for stylistic continuity. Furthermore, we employ MCLP as a reinforcement learning reward to enhance the style alignment between generated speech and role-play instructions. To support this task, we construct a large-scale RP-TTS dataset with rich scene and character annotations. Experiments demonstrate that MCLP is well aligned with human judgments of stylistic consistency and serves as an effective reward for improving RP-TTS, leading to consistent gains in both objective metrics and subjective evaluations. Our code is publicly available at https://github.com/y-ren16/MCLP. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Role-Play Text-to-Speech on Role-Play TTS Curated Evaluation Set (With Audio History)](): Role-Play Text-to-Speech; Role-Play TTS Curated Evaluation Set (With Audio History); CER: 1.13. - [Role-Play Text-to-Speech on Role-Play TTS Curated Evaluation Set Without Audio History](): Role-Play Text-to-Speech; Role-Play TTS Curated Evaluation Set Without Audio History; CER: 1.625. - [Role-Play Text-to-Speech on Role-Play TTS Curated Evaluation Set (Subjective)](): Role-Play Text-to-Speech; Role-Play TTS Curated Evaluation Set (Subjective); MOS: 3.646. ## Original sources and implementation [Original paper]() [PDF]()