Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

81–90 of 130 posts

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

#81

Post by magicalhippo »

ftyers wrote: post #9

Mozilla DeepSpeech trained on the Common Voice dataset for English. You can get pretrained models too. They have a nice matrix channel where you can get help, and pretty good documentation. It is also actively developed by several engineers. http://voice.mozilla.org/en/datasets and http://github.com/mozilla/DeepSpeech/

I had limited luck using the provided language model, but very good results when providing my own. So if you feel the results are poor, try building your own language model.

AFAIK DeepSpeech works by using the neural net to detect characters from speech, and then the language model is used to try to make a sentence out of the character stream, by doing a kind of graph search. Thus if the language model doesn't contain the words you want it to recognize, it'll have a hard time giving good output.

Anyway, I used the following tutorial[1] as a base to build the language model. For the kenlm tools I used Ubuntu WSL, and the generate_trie executable was part of the DeepSpeech native tools package for Windows.

[1]: https://discourse.mozilla.org/t/tutorial-how-i-trained-a-spe...

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

#82

Post by etrabroline »

byteshock wrote: post #79
guptaneil wrote: post #65

Disclaimer: I am the founder of Hiome, a smart home startup focused on private by design local-only products. What actions are you looking to handle with the assistant? Reason I ask is because a voice assistant is a command line interface with no auto-complete or visual feedback. It doesn’t scale well as you add more devices or commands to your home, because it becomes impossible to remember all the phrases you progr…

You really trying to promote your product? Corporate promotions really ruin the atmosphere... Take your corporate shilling elsewhere. I'm sure OP doesn't appreciate it.

I don't think mentioning your smart home startup in response to someone asking for recommendations for their smart home is unappreciated "corporate shilling".

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

#83

Post by mthoms »

byteshock wrote: post #79
guptaneil wrote: post #65

Disclaimer: I am the founder of Hiome, a smart home startup focused on private by design local-only products. What actions are you looking to handle with the assistant? Reason I ask is because a voice assistant is a command line interface with no auto-complete or visual feedback. It doesn’t scale well as you add more devices or commands to your home, because it becomes impossible to remember all the phrases you progr…

You really trying to promote your product? Corporate promotions really ruin the atmosphere... Take your corporate shilling elsewhere. I'm sure OP doesn't appreciate it.

From the site guidelines:

> Please don't post insinuations about astroturfing, shilling, brigading, foreign agents and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email us and we'll look at the data.

Besides, the commenter was upfront about their affiliation and offered insights that appear helpful to the discussion.

From elsewhere in the site guidelines:

> Assume good faith

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

#84

Post by detaro »

etrabroline wrote: post #82
byteshock wrote: post #79

Earlier quoted context omitted.

You really trying to promote your product? Corporate promotions really ruin the atmosphere... Take your corporate shilling elsewhere. I'm sure OP doesn't appreciate it.

I don't think mentioning your smart home startup in response to someone asking for recommendations for their smart home is unappreciated "corporate shilling".

It feels very borderline to me, given that it doesn't really address the question, but instead goes more like "actually, you don't want what you ask. instead, what I'm selling is better". At least that's how it comes across to me.

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

#85

Post by ghostpepper »

magicalhippo wrote: post #81
ftyers wrote: post #9

Mozilla DeepSpeech trained on the Common Voice dataset for English. You can get pretrained models too. They have a nice matrix channel where you can get help, and pretty good documentation. It is also actively developed by several engineers. http://voice.mozilla.org/en/datasets and http://github.com/mozilla/DeepSpeech/

I had limited luck using the provided language model, but very good results when providing my own. So if you feel the results are poor, try building your own language model. AFAIK DeepSpeech works by using the neural net to detect characters from speech, and then the language model is used to try to make a sentence out of the character stream, by doing a kind of graph search. Thus if the language model doesn't contai…

For a software engineer with no experience in machine learning / AI, what does it mean to build your own language model? Does it require coding? Hundreds of hours of audio data from your own voice? A significant amount of computing power?

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

#87

Post by detaro »

mthoms wrote: post #83
byteshock wrote: post #79

Earlier quoted context omitted.

You really trying to promote your product? Corporate promotions really ruin the atmosphere... Take your corporate shilling elsewhere. I'm sure OP doesn't appreciate it.

From the site guidelines: > Please don't post insinuations about astroturfing, shilling, brigading, foreign agents and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email us and we'll look at the data. Besides, the commenter was upfront about their affiliation and offered insights that appear helpful to the discussion. From elsewhere in the site guidelines: > Assume good fai…

I don't think that first rule applies here, precisely because they were upfront (and thus byteshock isn't insinuating some hidden motive, but directly criticizing what they said)

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

#88

Post by microtherion »

Apple platforms offer an API (SFSpeechRecognizer) which for some languages supports on-device recognition. Trivial to set up, super easy to use, and pretty reasonable accuracy.

Disclaimer: Working for Apple, not directly on this API but in related subjects.

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

#90

Post by magicalhippo »

ghostpepper wrote: post #85
magicalhippo wrote: post #81

Earlier quoted context omitted.

I had limited luck using the provided language model, but very good results when providing my own. So if you feel the results are poor, try building your own language model. AFAIK DeepSpeech works by using the neural net to detect characters from speech, and then the language model is used to try to make a sentence out of the character stream, by doing a kind of graph search. Thus if the language model doesn't contai…

For a software engineer with no experience in machine learning / AI, what does it mean to build your own language model? Does it require coding? Hundreds of hours of audio data from your own voice? A significant amount of computing power?

The tools available means you only need to provide a list of normal sentences, and they should include the words you'd like it to know about.

For my case I just wanted to train it on like 30 different sentences, that took less than a second. But for a general assistant ala Google Home you'll want a large number of sentences and I hear it can take a while (hour or few?).

Due to using probabilities it will match words in other sentences than what you give it, but from my understanding it will be partial to the ones you feed it if DeepSpeech mis-classifies a character or two.

Post reply on HN