TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Serverless speech recognition with WebAssembly

27 pointsby adrianbgover 7 years ago

3 comments

flavio81over 7 years ago
In this thread:<p>The Zork game, written in WebAssembly, using serverless (offline) speech recognition by using the Kaldi Speech Recognition Toolkit. Kaldi is written in C++ which then (i guess) is compiled into WebAssembly via Emscripten.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;kaldi-asr&#x2F;kaldi" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;kaldi-asr&#x2F;kaldi</a><p>Very very interesting.<p>Additional comment: When I saw the Amazon Alexa API (i was at a small meeting which included defining your own &quot;utterances&quot;, i was dissapointed that the Alexa required internet connection to perform the speech recognition, even moreso when the interaction with it was not so sophisticated (after all, it is geared to understanding predefined commands).
评论 #15534835 未加载
sjwalterover 7 years ago
Deadly. Have always hated the privacy implications of server-side speech processing.
gokover 7 years ago
Super super cool. What data did you use to train the acoustic model?
评论 #15545729 未加载