A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2002.11268/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition — mentioned by albertzeyerhttps://news.ycombinator.com/item?id=25905709urn:hackerpapers:mention:2002.11268:25905709Mon, 25 Jan 2021 17:07:34 GMT<p>This is like the density ratio approach (https://arxiv.org/abs/2002.11268). The Hybrid Autoregressive Transducer also uses a similar idea (https://arxiv.org/abs/2003.07705). Do you really need the renormalization, i.e. the outer softmax?</p><p><a href="https://hackerpaper.kaipfister.de/p/2002.11268/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS