# A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction

arXiv: https://arxiv.org/abs/2601.04960 · HTML: https://mlsanity.com/paper/2601.04960/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM](https://mlsanity.com/paper/2411.00774/) (2024)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [AI Flow: Perspectives, Scenarios, and Approaches](https://mlsanity.com/paper/2506.12479/) (2025)
- [WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark](https://mlsanity.com/paper/2406.05763/) (2024)
- [Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training](https://mlsanity.com/paper/1809.04505/) (2018)
- [BoSS: Beyond-Semantic Speech](https://mlsanity.com/paper/2507.17563/) (2025)
- [TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios](https://mlsanity.com/paper/2507.18061/) (2025)
- [GOAT-SLM: A Spoken Language Model with Paralinguistic and Speaker Characteristic Awareness](https://mlsanity.com/paper/2507.18119/) (2025)

## Built on by (most cited first, 1 of 1)

- [Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation](https://mlsanity.com/paper/2605.20946/) (2026)

## Abstract (arXiv)

This paper presents a unified spoken language model for emotional intelligence, enhanced by a novel data construction strategy termed Injected Emotional-Attribution Thinking (IEAT). IEAT incorporates user emotional states and their underlying causes into the model's internal reasoning process, enabling emotion-aware reasoning to be internalized rather than treated as explicit supervision. The model is trained with a two-stage progressive strategy. The first stage performs speech-text alignment and emotional attribute modeling via self-distillation, while the second stage conducts end-to-end cross-modal joint optimization to ensure consistency between textual and spoken emotional expressions. Experiments on the Human-like Spoken Dialogue Systems Challenge (HumDial) Emotional Intelligence benchmark demonstrate that the proposed approach achieves top-ranked performance across emotional trajectory modeling, emotional reasoning, and empathetic response generation under both LLM-based and human evaluations.