AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Hearing More with Less: Multi-Modal Retrieval-and-Selection Augmented Conversational LLM-Based ASR

Bingshen Mu, Hexin Liu, Hongfei Xue, Kun Wei, Lei Xie

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Speech and audio language models · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add current-utterance hypothesis as input to LLM-ASR (ablation)LLM-ASR · MLC-SLM testMER (%): 11.04 -> 9.89Improved
add top-1 text-retrieved historical context (ablation)LLM-ASR + Hyp. · MLC-SLM testMER (%): 9.89 -> 9.23Improved
add top-1 speech-retrieved historical context (ablation)LLM-ASR + Hyp. · MLC-SLM testMER (%): 9.89 -> 9.41Improved
combine top-1 speech and top-1 text retrieved contexts without selection (ablation)MARS · MLC-SLM testMER (%): 9.23 -> 9.34Hurt
add multi-modal selection with near-ideal ranking (ablation)MARS · MLC-SLM testMER (%): 9.34 -> 8.96Improved
add two-pass decoding (ablation)MARS · MLC-SLM testMER (%): 8.96 -> 8.35Improved
increase number of preceding utterances used as context (ablation)LLM-ASR · MLC-SLM testMER (%): 9.74 (1 context) -> 13.49 (5 contexts)Hurt
use retrieved context instead of the same number of preceding contexts (ablation)LLM-ASR · MLC-SLM testMER (%): 9.74 (Context{1}) -> 9.41 (speech Top-1) / 9.23 (text Top-1)Improved
use near-ideal ranking instead of summing speech and text similarities (ablation)MARS selection · MLC-SLM testMER (%): 9.18 -> 8.96Improved
use all 2K retrieved contexts instead of selecting the best one (ablation)MARS · MLC-SLM testMER (%): 8.96 -> 11.24 (2xTop-3)Hurt
use ground-truth preceding contexts in prior methodsBi-context / Seewo · MLC-SLM devMER (%): Seewo 15.48 -> 14.30; Bi-context 14.87 -> 13.16Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy