Signals 4 · free daily AI digest

Merging the Knowledge of LLMs for Automatic Speech Recognition

Paper recorded by Signals 4 on 2026-09-14 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-14 on arXiv · recorded by Signals 4 on 2026-09-15

Category: cs.CL · 自然语言处理 · first seen 2026-09-15

Abstract

Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods such as shallow fusion and density ratio are well-established methods that incorporate external LMs during ASR decoding. However, they incur additional computational costs due to LM inference, which is particularly probl

Read on arXiv →

#47 most recent of 186 cs.CL papers we have recorded · ↑ newer: Look Before You Leap: Factual Decoding with Internal Attribution Signa · ↓ older: Data storytelling meets interpretable machine learning: Decoding AI de
Cite this page: Merging the Knowledge of LLMs for Automatic Speech Recognition: the #47 most recent of 186 cs.CL papers we have recorded (as of 2026-09-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/merging-the-knowledge-of-llms-for-automatic-speech-recognition.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions