# Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment

arXiv: https://arxiv.org/abs/2604.11424 · HTML: https://mlsanity.com/paper/2604.11424/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 51 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 25 of 25)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction](https://mlsanity.com/paper/2502.11946/) (2025)
- [Fun-Audio-Chat Technical Report](https://mlsanity.com/paper/2512.20156/) (2025)
- [LUCY: Linguistic Understanding and Control Yielding Early Stage of Her](https://mlsanity.com/paper/2501.16327/) (2025)
- [Differentiable Reward Optimization for LLM based TTS system](https://mlsanity.com/paper/2507.05911/) (2025)
- [SpeechJudge: Towards Human-Level Judgment for Speech Naturalness](https://mlsanity.com/paper/2511.07931/) (2025)
- [Scaling Analysis of Interleaved Speech-Text Language Models](https://mlsanity.com/paper/2504.02398/) (2025)
- [Self-Improvement for Audio Large Language Model using Unlabeled Speech](https://mlsanity.com/paper/2507.20169/) (2025)
- [VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions](https://mlsanity.com/paper/2509.09716/) (2025)
- [Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation](https://mlsanity.com/paper/2408.11849/) (2024)
- [EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection](https://mlsanity.com/paper/2506.09827/) (2025)
- [Empathy Omni: Enabling Empathetic Speech Response Generation through Large Language Models](https://mlsanity.com/paper/2508.18655/) (2025)
- [Explore the Reinforcement Learning for the LLM based ASR and TTS system](https://mlsanity.com/paper/2509.18569/) (2025)
- [UltraVoice: Scaling Fine-Grained Style-Controlled Speech Conversations for Spoken Dialogue Models](https://mlsanity.com/paper/2510.22588/) (2025)

## Abstract (arXiv)

Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened prosody and misaligned emotion. We identify this mismatch as the semantic understanding-acoustic realization gap. Existing approaches typically rely on externally specified proxies, such as emotion labels or style prompts, which require annotations and struggle to capture dynamically evolving expressive intent throughout dialogue. To overcome these limitations, we propose SASLM (Self-Aware Speech Language Model), a proxy-free framework that bridges what the model thinks and how it speaks through self-aware intent-realization alignment: (1) Intent-Aware Bridging self-distills expressive intent from the model's own evolving semantic generation states via a Variational Information Bottleneck (VIB), thereby guiding expressive speech realization without external expressive supervision; while (2) Realization-Aware Alignment reflectively aligns generated acoustics with intended expression through self-reward optimization, progressively improving intent-realization consistency during speech generation. Despite using only 3B parameters and 800 hours of expressive speech data, SASLM achieves state-of-the-art performance on EchoMind among open-source systems, surpassing models over 10 times larger and approaching commercial systems.