Deep convolutional acoustic word embeddings using word-pair side information · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1510.01032/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDeep convolutional acoustic word embeddings using word-pair side information — mentioned by kastnerkylehttps://news.ycombinator.com/item?id=12680301urn:hackerpapers:mention:1510.01032:12680301Mon, 10 Oct 2016 22:35:15 GMT<p>There are a number of papers tackling a similar task [0][1][2] for anyone who is interested. There isn&#x27;t enough information to tell exactly what is going on with Deepgram, but one way to approach this would be to construct a shared embedding space for words/phrases and speech. These types of embedding spaces are powerful [3][4][5], but not magic. Cool demo, looking forward to seeing more detail about what is going on. However I would quibble with the STT WER quoted above. Maybe in noisy environments with unknown speakers (and no voice normalization) this is accurate, but the kinds of clean…</p><p><a href="https://hackerpaper.kaipfister.de/p/1510.01032/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL