SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2110.05571/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSRU++: Pioneering Fast Recurrence with Attention for Speech Recognition — mentioned by Smerityhttps://news.ycombinator.com/item?id=41736930urn:hackerpapers:mention:2110.05571:41736930Fri, 04 Oct 2024 01:31:57 GMT<p>Excited to see more people working on RNNs but wish their citations were better. In 2016 my team from Salesforce Research published our work on the Quasi-Recurrent Neural Network[1] (QRNN). The QRNN variants we describe are near identical (minGRU) or highly similar (minLSTM) to the work here. The QRNN was used, many years ago now, in the first version of Baidu&#x27;s speech recognition system (Deep Voice [6]) and as part of Google&#x27;s handwriting recognition system in Gboard[5] (2019). Even if there are expressivity trade-offs when using parallelizable RNNs they&#x27;ve shown historically they can work…</p><p><a href="https://hackerpaper.kaipfister.de/p/2110.05571/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS