State-of-the-art Speech Recognition With Sequence-to-Sequence Models · HackerPapers discussions

State-of-the-art Speech Recognition With Sequence-to-Sequence Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1712.01769/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTState-of-the-art Speech Recognition With Sequence-to-Sequence Models — mentioned by kastnerkylehttps://news.ycombinator.com/item?id=16672609urn:hackerpapers:mention:1712.01769:16672609Sun, 25 Mar 2018 15:34:35 GMT<p>This has changed recently, full seq2seq is now matching hybrid models [0]. [0] https://arxiv.org/abs/1712.01769</p><p><a href="https://hackerpaper.kaipfister.de/p/1712.01769/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL