Uncovering Latent Style Factors for Expressive Speech Synthesis · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1711.00520/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTUncovering Latent Style Factors for Expressive Speech Synthesis — mentioned by yomansathttps://news.ycombinator.com/item?id=16022272urn:hackerpapers:mention:1711.00520:16022272Thu, 28 Dec 2017 14:57:46 GMT<p>I found this from ~3 months ago, the recent addition to github: https://google.github.io/tacotron/publications/uncovering_la... Seems to do with manipulating the speed styles in how we speak. Listen to the &quot;neutral&quot; blue lagoon, vs token 6 (tired sound), vs mix w/ token 7 (prominence)&quot; (very confident). Paper: https://arxiv.org/pdf/1711.00520.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1711.00520/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL