LaSR: Context-Aware Speech Recognition via Latent Reasoning

arXiv:2606.00507 · cs.CL · Submitted 2026-05-30 · Read on arXiv

cs.CL

Submitted: 2026-05-30

Updated: 2026-09-17

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Latent Reasoning — 30× in this paper · explained in 2 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Verification — 8× in this paper · explained in 2 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Anisotropy — 3× in this paper · explained in 3 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 3× in this paper · explained in 4 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Chain of Thought — 2× in this paper
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Causal Reasoning — 1× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Contextual Awareness — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Speech LLMs are Contextual Reasoning Transcribers
• CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
• Training Large Language Models to Reason in a Continuous Latent Space
• Qwen3-TTS Technical Report
• Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
• Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
• Qwen3-ASR Technical Report
• Fun-Audio-Chat Technical Report
• Step-Audio-R1 Technical Report
• Step-Audio 2 Technical Report
• Qwen2.5-Omni Technical Report
• Qwen3-Omni Technical Report
• LIMO: Less is More for Reasoning
• GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
• MiMo-Audio: Audio Language Models are Few-Shot Learners
• Step-Audio-R1.5 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering