SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2209.15329/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data — mentioned by reliableturinghttps://news.ycombinator.com/item?id=35369678urn:hackerpapers:mention:2209.15329:35369678Thu, 30 Mar 2023 08:29:00 GMT<p>This is exactly part of this Google USM approach, although these pretrained models are significantly smaller than ChatGPT. They reference this paper [1] which contains more details on the pretrained text-only alignment with the speech model. [1] https://arxiv.org/abs/2209.15329</p><p><a href="https://hackerpaper.kaipfister.de/p/2209.15329/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL