Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving

arXiv:2607.01733 · cs.CL, eess.AS · Submitted 2026-07-02 · Read on arXiv

cs.CL, eess.AS

Submitted: 2026-07-02

Updated: 2026-09-20

Comments: Accepted to SLT 2026, camera-ready version

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

Terminology

• Alignment — 19× in this paper · explained in 1 episode
• LLM Integration — 12× in this paper · explained in 2 episodes
• Adaptation — 10× in this paper · explained in 1 episode
• Modality Gap — 10× in this paper · explained in 4 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Joint Speech-Text Interleaved Pretraining — 5× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Domain Adaptation — 2× in this paper · explained in 5 episodes
• Entity Error Rate — 2× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Zero-shot Speech Question Answering — 2× in this paper
• AlignFormer — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Token Error Rate — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• GPT-4 Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• DeepSeek-V3 Technical Report
• Gemma 3 Technical Report
• Qwen3 Technical Report
• Moshi: a speech-text foundation model for real-time dialogue
• Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
• Kimi-Audio Technical Report
• Step-Audio 2 Technical Report
• Qwen3-Omni Technical Report
• SLM-S2ST: A multimodal language model for direct speech-to-speech translation
• Fun-Audio-Chat Technical Report
• FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
• Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
• Fun-ASR Technical Report
• Index-ASR Technical Report
• Efficient Scaling for LLM-based ASR
• Qwen3-ASR Technical Report
• Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
• Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio

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