https://hackerpaper.kaipfister.de/p/1708.06073/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=16321851urn:hackerpapers:mention:1708.06073:16321851Wed, 07 Feb 2018 02:37:20 GMT<p>Who am I to argue with your experience? I can only offer the current literature on the topic [0]. (They report a 5.1% error) &gt; These systems typically use deep convolutional neural network (CNN) architectures ... driving the word error rate on the benchmark Switchboard corpus down from its mid-2000s plateau of around 15% to well below 10%. [0]: https://arxiv.org/pdf/1708.06073.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1708.06073/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL