Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1910.06379/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation — mentioned by lapinkhttps://news.ycombinator.com/item?id=21664390urn:hackerpapers:mention:1910.06379:21664390Fri, 29 Nov 2019 14:00:27 GMT<p>Speech source separation has gone a long way, thanks to Yi Luo amazing work. With Dual Path RNN, he now achieves almost 20 Signal to Noise Ratio for 2 speaker separation, see [1]. This is a bit of an artificial setting though, only two speakers and they are manually mixed together. I&#x27;m not sure if there is any good dataset of speech source separation in real environments (an airport, restaurant etc). [1]: https://arxiv.org/pdf/1910.06379.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1910.06379/">Paper and discussion history</a>. A mention is not an endorsement.</p>eess.AS