[dwa3592]

this is good to see. i also trained a stt under 500kb for sub dollar chips. it had about 20 words that it could understand(like start, stop, left, right, go, up etc) and then the spell mode where you could say the word spell and then say the individual english alphabets and close with spell. it was super fun to work on. these tend to be extremely unstable though, like confusion between p and t (at least for my accent). will have to try this one now.

[NooneAtAll3]

I remember someone training smart kettle to use its speaker as microphone

[schoen]

Could you get people to use the NATO phonetic alphabet for the spelling part? I suppose a challenge is that many people don't know the whole thing, even if they're aware it exists.

[jodrellblank]

NATO phonetic is to be understandable over a noisy radio channel, if you want just distinct sounds then Talon Voice users settled on shorter ones easier to use all the time:

    air a
    bat b
    cap c
    drum d
    each e
    fine f
    gust g
    harp h
    sit i
    jury j
    crunch k
    look l
    made m
    near n
    odd o
    pit p
    quench q
    red r
    sun s
    trap t
    urge u
    vest v
    whale w
    plex x
    yank y
    zip z

[close2]

Interesting, that some words don't start with the letter they represent.

[otikik]

“Plex” ?

[jodrellblank]

a) I went to a Talon Voice cheat sheet and copied them out because I didn’t remember them. Is plex not right?

b) Talon Voice is a configurable voice engine, the commands are something you setup and people use common shared starter packs and then edit their own, so there isn’t a formal standard, plex might be different in some setups?

c) they just have to be sounds you can vocalise which are distinct from each other, and it helps if they are one syllable when using them often; there’s no reason they have to be dictionary words or mean anything.

[schoen]

There's presumably a lot of benefit to having stable and widespread standards in this area (so people can re-use their skills!). So hopefully this is now stable at least within this community.

[otikik]

But all of the other words begin with the letter they represent. Plex ends with it. It sticks out quite a lot.

One could make "Pit" be "t", with that logic.

[schoen]

This property is also not true for "sit" or "crunch".

[laidoffamazon]

IIRC the Alexa enabled voice remotes also used a similarly small model though perhaps not this small