RLAIF-SPA: Optimizing LLM-based Emotional Speech Synthesis via RLAIF

• URL: http://arxiv.org/abs/2510.14628v1
• Date: Thu, 16 Oct 2025 12:40:37 GMT
• Title: RLAIF-SPA: Optimizing LLM-based Emotional Speech Synthesis via RLAIF
• Abstract summary: Text-To-Speech synthesis has achieved near-human quality in neutral speech, but emotional expressiveness remains a challenge.<n>We propose the RLAIF-SPA framework, incorporating a Reinforcement Learning from AI Feedback mechanism to employ Automatic Speech Recognition (ASR) and Large Language Model (LLM) techniques.<n>Experiments on the Libri Speech dataset show that RLAIF-SPA outperforms Chat-TTS, with a 26.1% reduction in WER, a 9.1% increase in SIM-O, and over 10% improvement in human evaluation.
• Score: 23.474332076771308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-To-Speech synthesis has achieved near-human quality in neutral speech, but emotional expressiveness remains a challenge. Existing methods often rely on costly emotion annotations or optimize indirect objectives that fail to capture the emotional expressiveness and perceptual naturalness of speech, leading to generated speech that is accurate but emotionally flat. To address these challenges, we propose the RLAIF-SPA framework, incorporating a Reinforcement Learning from AI Feedback (RLAIF) mechanism to employ Automatic Speech Recognition (ASR) and Large Language Model (LLM) techniques to respectively judge semantic accuracy and prosodic-emotional label alignment as a direct reward for emotional expressiveness and intelligibility optimization. Specifically, it leverages Prosodic Label Alignment to enhance expressive quality by jointly considering semantic accuracy and prosodic-emotional alignment along four fine-grained dimensions: Structure, Emotion, Speed, and Tone. In addition, it incorporates Semantic Accuracy Feedback to ensure the generation of clear and accurate speech. Experiments on the Libri Speech dataset show that RLAIF-SPA outperforms Chat-TTS, with a 26.1% reduction in WER, a 9.1% increase in SIM-O, and over 10% improvement in human evaluation.

Related papers

• On the Emotion Understanding of Synthesized Speech [63.13411068766772]
  Emotion is a core paralinguistic feature in voice interaction.<n>Current Speech Emotion Recognition (SER) models can not generalize to synthesized speech.<n>generative Speech Language Models (SLMs) tend to infer emotion from textual semantics while ignoring paralinguistic cues.
  arXiv  Detail & Related papers  (2026-03-17T13:11:14Z)
• Causal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2 [0.0]
  We propose a causal prosody mediation framework for expressive text-to-speech synthesis.<n>Our approach augments the FastSpeech2 architecture with explicit emotion conditioning.<n>We observe better intelligibility (low WER) and speaker consistency when transferring emotions across speakers.
  arXiv  Detail & Related papers  (2026-03-12T08:48:01Z)
• VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs [54.75016325571445]
  Speech Large Language Models (LLMs) show great promise for speech emotion recognition via generative interfaces.<n> shifting from closed-set to open text generation introduces zero-shotity, making evaluation highly sensitive to prompts.<n>We present VoxEmo, a comprehensive SER benchmark encompassing 35 emotion corpora across 15 languages for Speech LLMs.
  arXiv  Detail & Related papers  (2026-03-09T21:10:34Z)
• ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning [67.22219034602514]
  We introduce ADEPT (Agentic Decoding of Emotion via Evidence Probing Tools), a framework that reframes emotion recognition as a multi-turn inquiry process.<n> ADEPT transforms an SLLM into an agent that maintains an evolving candidate emotion set and adaptively invokes dedicated semantic and acoustic probing tools.<n>We show that ADEPT improves primary emotion accuracy in most settings while substantially improving minor emotion characterization.
  arXiv  Detail & Related papers  (2026-02-13T08:33:37Z)
• EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis [36.831497786147864]
  We present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer.<n>EmoShift learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression.<n>With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations.
  arXiv  Detail & Related papers  (2026-01-30T11:50:23Z)
• ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation [30.006550552714938]
  Empathetic speech dialogue requires not only understanding linguistic content but also perceiving rich paralinguistic information.<n>Existing speech-to-speech large language models either rely on ASR transcription or use encoders to extract latent representations.<n>We propose textbfES4R, a framework for speech-based empathetic response generation.
  arXiv  Detail & Related papers  (2026-01-16T10:26:50Z)
• Plug-and-Play Emotion Graphs for Compositional Prompting in Zero-Shot Speech Emotion Recognition [3.1649536621597973]
  Large audio-language models (LALMs) exhibit strong zero-shot performance across speech tasks but struggle with speech emotion recognition (SER)<n>We propose Compositional Chain-of-Thought Prompting for Emotion Reasoning (CCoT-Emo) to guide LALMs in emotion inference without fine-tuning.
  arXiv  Detail & Related papers  (2025-09-29T20:06:03Z)
• EmoCAST: Emotional Talking Portrait via Emotive Text Description [56.42674612728354]
  EmoCAST is a diffusion-based framework for precise text-driven emotional synthesis.<n>In appearance modeling, emotional prompts are integrated through a text-guided decoupled emotive module.<n>EmoCAST achieves state-of-the-art performance in generating realistic, emotionally expressive, and audio-synchronized talking-head videos.
  arXiv  Detail & Related papers  (2025-08-28T10:02:06Z)
• From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition [7.362433184546492]
  Dynamic Facial Expression Recognition aims to identify human emotions from temporally evolving facial movements.<n>Our method integrates dynamic motion modeling, semantic text refinement, and token-level cross-modal alignment to facilitate the precise localization of emotionally salient features.
  arXiv  Detail & Related papers  (2025-07-16T04:15:06Z)
• MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition [1.894337673869513]
  This paper presents our contributions to the Speech Emotion Recognition in Naturalistic Conditions (SERNC) Challenge.<n>To handle the complexities of natural speech, we propose Multi-level Acoustic-Textual Emotion Representation (MATER)<n>MATER integrates acoustic and textual features at the word, utterance, and embedding levels.
  arXiv  Detail & Related papers  (2025-06-24T05:35:53Z)
• VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection [50.57849622045192]
  We propose VAEmo, an efficient framework for emotion-centric joint VA representation learning with external knowledge injection.<n>VAEmo achieves state-of-the-art performance with a compact design, highlighting the benefit of unified cross-modal encoding and emotion-aware semantic guidance.
  arXiv  Detail & Related papers  (2025-05-05T03:00:51Z)
• GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations [35.63053777817013]
  GatedxLSTM is a novel multimodal Emotion Recognition in Conversation (ERC) model.<n>It considers voice and transcripts of both the speaker and their conversational partner to identify the most influential sentences driving emotional shifts.<n>It achieves state-of-the-art (SOTA) performance among open-source methods in four-class emotion classification.
  arXiv  Detail & Related papers  (2025-03-26T18:46:18Z)
• UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts [64.02363948840333]
  UMETTS is a novel framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech.<n>EP-Align employs contrastive learning to align emotional features across text, audio, and visual modalities, ensuring a coherent fusion of multimodal information.<n>EMI-TTS integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions.
  arXiv  Detail & Related papers  (2024-04-29T03:19:39Z)
• An Attribute-Aligned Strategy for Learning Speech Representation [57.891727280493015]
  We propose an attribute-aligned learning strategy to derive speech representation that can flexibly address these issues by attribute-selection mechanism. Specifically, we propose a layered-representation variational autoencoder (LR-VAE), which factorizes speech representation into attribute-sensitive nodes. Our proposed method achieves competitive performances on identity-free SER and a better performance on emotionless SV.
  arXiv  Detail & Related papers  (2021-06-05T06:19:14Z)
• Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability [82.39099867188547]
  Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years. We propose a new interactive training paradigm for ETTS, denoted as i-ETTS. We formulate an iterative training strategy with reinforcement learning to ensure the quality of i-ETTS optimization.
  arXiv  Detail & Related papers  (2021-04-03T13:52:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.