# LaSR: Context-Aware Speech Recognition via Latent Reasoning

arXiv: https://arxiv.org/abs/2606.00507 · HTML: https://mlsanity.com/paper/2606.00507/

## 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 16 of its 36 references that are in the map.
- First posted on arXiv 30 May 2026.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Qwen3-TTS Technical Report](https://mlsanity.com/paper/2601.15621/) (2026)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering](https://mlsanity.com/paper/2503.11197/) (2025)
- [Step-Audio-R1 Technical Report](https://mlsanity.com/paper/2511.15848/) (2025)
- [Fun-Audio-Chat Technical Report](https://mlsanity.com/paper/2512.20156/) (2025)
- [Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training](https://mlsanity.com/paper/2602.07824/) (2026)
- [Contextual Biasing for LLM-Based ASR with Hotword Retrieval and Reinforcement Learning](https://mlsanity.com/paper/2512.21828/) (2025)
- [Speech LLMs are Contextual Reasoning Transcribers](https://mlsanity.com/paper/2604.00610/) (2026)

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

- [S3-Bench: Evaluating Speech Interaction Models as Scientific Voice Assistants](https://mlsanity.com/paper/2609.09852/) (2026)

## Abstract (arXiv)

Speech recognition in specialized domains requires leveraging contextual or topical information to improve the recognition of domain-specific entities. Speech Large Language Models (Speech LLMs) have substantially advanced speech understanding and reasoning capabilities, making context-aware speech recognition possible without predefined bias lists. In this paper, we propose LaSR (Latent Speech Reasoning), a novel training paradigm featuring a context-aware reasoning trajectory that leverages the latent reasoning process. Instead of generating explicit intermediate tokens, LaSR aligns chain-of-thought (CoT) supervision around the acoustic feature region of the target word, and introduces latent reasoning periods for context information grounding and transcriptional transition. Furthermore, to effectively benchmark context-aware speech recognition, we propose Spoken Darwin-Science, a large-scale corpus focusing on academic terminologies. Preliminary experiments on Fun-Audio-Chat demonstrate that LaSR significantly improves terminology recognition without introducing additional latency and consistently outperforms standard supervised fine-tuning baselines. Our findings highlight the potential of latent reasoning in building efficient, context-aware speech assistants.