Ask HN: Non-cloud voice recognition for home use? • Hacker News Board

Re: Ask HN: Non-cloud voice recognition for home use?

#51

Post by otodic » Sat, Mar 14, 2020, 7:44 PM UTC

My company develops SDKs for on-device speech recognition on Android/iOS: https://keenresearch.com/keenasr-docs (Raspberry Pi is an option too, we'll have a GA release in Q2)

We license this on commercial bases but would be open to indy-developer friendly licensing. We offer a trial SDK that makes testing/evaluation super easy (it works for 15min at the time).

Ogi

ogi@keeenresearch.com

Re: Ask HN: Non-cloud voice recognition for home use?

#52

Post by rs23296008n1 » Sat, Mar 14, 2020, 7:44 PM UTC

lunixbochs wrote: post #42

Hi, I'm the dev behind https://talonvoice.com I've been working with Facebook's wav2letter project and the results (speed on CPU, command accuracy) are extremely good in my experience. They also hold the "state of the art" for librispeech (a common benchmark) on wer_are_we [1]. Granted, that's with a 2GB model that doesn't run very well on CPU, but I think most of the fully "state of the art" models are computational…

Looks interesting. I've got a few GPUs I could use if the CPU is too much of a bottleneck.

We've identified a dictionary of the types of commands and words we use and have a recording of all our amazon and other commands. Training wave files are not an issue.

Have you had any issues with recognising multiple languages?

Thanks!

Re: Ask HN: Non-cloud voice recognition for home use?

#53

Post by lunixbochs » Sat, Mar 14, 2020, 7:56 PM UTC

rs23296008n1 wrote: post #52

lunixbochs wrote: post #42

Hi, I'm the dev behind https://talonvoice.com I've been working with Facebook's wav2letter project and the results (speed on CPU, command accuracy) are extremely good in my experience. They also hold the "state of the art" for librispeech (a common benchmark) on wer_are_we [1]. Granted, that's with a 2GB model that doesn't run very well on CPU, but I think most of the fully "state of the art" models are computational…

Looks interesting. I've got a few GPUs I could use if the CPU is too much of a bottleneck. We've identified a dictionary of the types of commands and words we use and have a recording of all our amazon and other commands. Training wave files are not an issue. Have you had any issues with recognising multiple languages? Thanks!

Are you talking about recognizing multiple languages at once (e.g. you don't know which language the user will speak and you want it to react appropriately to all of them)? You're going to have a harder time doing that with any system, but it is possible. You would likely need to run multiple models and pick between their output, or train a specialized separate model that can classify the language, then use it to pick the model.

I haven't personally tested wav2letter with other languages yet. I know zamia-speech trained a german model, and some users have been talking about training for other languages. I've been helping someone who is training several other languages and they've reported great success as well.

If you want to make a new model from scratch in any language, you'll probably want a couple hundred hours of transcribed speech for it, but it doesn't need to be your own speech. Common Voice is a good data source for that.

Re: Ask HN: Non-cloud voice recognition for home use?

#54

Post by amenod » Sat, Mar 14, 2020, 8:27 PM UTC

Shawnecy wrote: post #20

saghm wrote: post #16

Earlier quoted context omitted.

Is there any product where self-hosting _isn't_ more difficult? That seems like a generic warning that could apply to pretty much any product in this space. It seems more like a warning to non-technical users who might not have the experience or know-how to successfully set up a server.

If it was simply an issue of just "more difficult", then it wouldn't be worth pointing out. However, the words "significantly more challenging to manage" are straight from their documentation that I linked which I think makes it worth pointing out. Whether or not it is too challenging is for each individual to decide for themselves.

It also gives an indication what the preferred method of deployment is (from authors' point of view). In this case I read it as a warning that it might stop being supported in the future.

Re: Ask HN: Non-cloud voice recognition for home use?

#55

Post by stragies » Sat, Mar 14, 2020, 8:43 PM UTC

rs23296008n1 wrote: post #21

arendtio wrote: post #13

Earlier quoted context omitted.

Did you visit the website lately? Doesn't seem to be an option anymore :-/

They only seem to do audio equipment. Did they once do more things more general?

Before they were bought, you could build (with the help of a WebApp hosted by them) an offline usable speech recognition module, that could comfortably run on a Pi, and that would output parsed sentences in JSON format onto MQTT. Easy to integrate with everything in IOT. I loved it. Now i'm also looking for an alternative for the Speech-to-text(-to-json) part, like you.

Re: Ask HN: Non-cloud voice recognition for home use?

#56

Post by stragies » Sat, Mar 14, 2020, 8:48 PM UTC

rs23296008n1 wrote: post #52

lunixbochs wrote: post #42

Hi, I'm the dev behind https://talonvoice.com I've been working with Facebook's wav2letter project and the results (speed on CPU, command accuracy) are extremely good in my experience. They also hold the "state of the art" for librispeech (a common benchmark) on wer_are_we [1]. Granted, that's with a 2GB model that doesn't run very well on CPU, but I think most of the fully "state of the art" models are computational…

Looks interesting. I've got a few GPUs I could use if the CPU is too much of a bottleneck. We've identified a dictionary of the types of commands and words we use and have a recording of all our amazon and other commands. Training wave files are not an issue. Have you had any issues with recognising multiple languages? Thanks!

My "workaround" for using offline recognition in several languages in `snips.ai` was configuring a different wake-word per language, and then running several wake-word-detectors on the same microphone input.

Re: Ask HN: Non-cloud voice recognition for home use?

#57

Post by stragies » Sat, Mar 14, 2020, 8:54 PM UTC

belbob wrote: post #35

maybe https://jasperproject.github.io/

Jasper is another project that uses CMUSPINX from https://cmusphinx.github.io/wiki/faq/ under the hood.

Re: Ask HN: Non-cloud voice recognition for home use?

#58

Post by Animats » Sat, Mar 14, 2020, 8:56 PM UTC

Is there a voice dialer for Android that doesn't use Google? There used to be, but it disappeared in the "upgrade" which has the mothership listening all the time.

Re: Ask HN: Non-cloud voice recognition for home use?

#59

Post by lunixbochs » Sat, Mar 14, 2020, 8:58 PM UTC

otodic wrote: post #51

My company develops SDKs for on-device speech recognition on Android/iOS: https://keenresearch.com/keenasr-docs (Raspberry Pi is an option too, we'll have a GA release in Q2) We license this on commercial bases but would be open to indy-developer friendly licensing. We offer a trial SDK that makes testing/evaluation super easy (it works for 15min at the time). Ogi ogi@keeenresearch.com

> Currently, the SDK supports English and Spanish out of the box. Additional ASR Bundles for most major spoken languages can be provided upon request within 6-8 weeks.

Does this mean you have a standing offer to train a new language on demand?

Re: Ask HN: Non-cloud voice recognition for home use?

#60

Post by stevewilhelm » Sat, Mar 14, 2020, 9:02 PM UTC

Question, what aspect of your product restricts the software architecture to not use "off-site cloud?"