Merging the Knowledge of LLMs for Automatic Speech Recognition

arXiv:2609.15743 · cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CL

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: Accepted to Interspeech2026

Code: https://github.com/arcee-ai/mergekit

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

Terminology

• Adaptation — 17× in this paper · explained in 1 episode
• Model Merging — 14× in this paper · explained in 2 episodes
• Domain Adaptation — 10× in this paper · explained in 5 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Automatic Speech Recognition (ASR) — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Corpus of Spontaneous Japanese — 2× in this paper
• Distillation — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Alignment Problem — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• The Llama 3 Herd of Models
• Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
• Kimi-Audio Technical Report
• Qwen3-Omni Technical Report
• LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
• Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over
• Task Arithmetic for Language Expansion in Speech Translation
• Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Transport and Merge: Cross-Architecture Merging for Large Language Models

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