Hacker News new | ask | show | jobs
by adrianbg 2965 days ago
Alexa does most of the hard stuff: speech recognition / intent detection, and speech synthesis.

My back end is a simple Python service on GCP that handles HTTP requests from Alexa. The same service also downloads the HN front page from the FireBase mirror and gets summaries from this API:

https://rapidapi.com/textanalysis/api/Text%20Summarization

It's not perfect though, so I may switch to a more expensive summarization API, supplement it with manual summaries, and/or train my own summarization model.

1 comments

Thank you, I didn't know Alexa handled all of that.
Sometimes I wish it didn't. They don't give you the original audio, any kind of confidence score, or even alternative hypotheses. It's really a pretty rigid platform. A lot of things that seem like they should be reasonable are impossible. Eg., I'd prefer to just say a list of post titles and let people interrupt Alexa when they hear something they like. That is impossible right now without pretty serious hacks.
Yeah, I was working on an Alexa skill once where I wanted the user to be able to say anything. That isn’t possible really, unless you give Alexa a really long randomly generated list of un-related/non-existent words for the “intent”, so that when Alexa tries to parse what the user says to those words, it fails and just provides its next best guess.
Google's speech recognition is supposed to be much better, though not sure if they'd allow "one intent to rule them all" like you want.

For free-form speech recognition in Alexa, the best option I've seen mentioned on the public Alexa Slack team is using the "SearchQuery" slot. So you'd still have to make a weird catch-all intent that would eat up some of the words (and you wouldn't be able to see them). At the same time, you shouldn't assume that Alexa will give you very good results with such loose constraints. Even in my simple skill it's very bad about confusing certain pairs of words.

Might have to try google home.

As an aside, did you hit 100 enables yet? If so, congrats on the free dot :)

I.... don't know. But I doubt it :)