Microphone advise for PI2 & voice control

richland007

@joern said in Microphone advise for PI2 & voice control:

respeaker 4mic array

I have a question can i use 2 microphones on a raspberry pi ?? Either usb or something like the respeaker where both mics are monitored by different modules one for MM-voice and the other for Alexa Pi … (MM-voice will let you choose a mic ID, where it listens to its wake words)
I Just don’t know how to have raspberry pi’s configuration twitched, which i am sure it needs to be, to have 2 mics working???
Denis

maxbachmann

Why wouldn’t you use the same for both? makes not much sence to use two microphone arrays when both modules can just listen to the same. Or do you mean to have mics in multiple rooms? Two respeaker is not really possible since they would use the same GPIO pins, but yes in general you could connect another one over USB. just can’t see why you would want to do this

A Former User

@richland007
I have no idea why you want to find a good mic, but with my experience, the cheapest mini USB mic from Amazon is too enough for the most purpose of vocal input.

maxbachmann

@Sean @richland007 Well I guess that highly depends on what you want to achieve xD
I would go cracy with my voice recogntion without a decent Mic array.

But yes when your in a pretty quiet environment and only using it with MM2 --> standing in front of the mirror --> small distance a cheap mic should absolutely be enough.
My minimal needs for a voice recognition are around 5m (obviously without shouting) distance :smiling_face_with_open_mouth_cold_sweat:

However I can’t think of any purpose where two mics would make sence at one device for two modules. Only thing that would make sence is having one mic in each room streaming the audio to a main device that does the speech recognition work (comparable to Alexa with the echo dots)

Well for a cheap one my suggestion would be a respeaker two mic hat (9.9$).

richland007

@maxbachmann @Sean It is my understanding that not 2 separate programs (AlexaPi and MMM-voice) use the same resources which is the one and only usb microphone i have right now.
Am i right on this??.. cause boy do i wish to be wrong!!
Has anyone used 2 progs one mic…and i haven’t even tired it but someone said you couldn’t and i think they are right myself… but i will give it a try and hope it works.

maxbachmann

@richland007 it definetly works. and why should it not? On the spur of the moment I can’t think of any pc connected device that works with only one software (well excluding some proprietary devices that work only with the company’s stuff).
However for example Mouse, Keyboard, speakers, microphone … all definetly work with multiple programs. The components are always connected to the OS, so any software running on that OS can generally ask it for the informations.
I mean if I wanted I could even split for example the cable of the microphone and connect t to two computers and it would work ^^
I never used Alexa Pi, since it is cloud based and I am no big fan of putting my stuff in the cloud, but usually when setting up voice recognitions, you tell which microphone to listen to

And as an example where you use one muc for 2 programs: when you play video games with a voice chat program in the background and still use the ingame chat ;)

A Former User

I cannot assure, but there could be a possibility of resource possession.
With my experience, Hotword catching program should always hold Mic on to listen the hotwords, so when 2 programs are trying to get a mic together, there would become fails.
I don’t know whether AlexaPi and MMM-Voice are those kinds of program, But without proper pre-processor program for distributing and controlling mic, the two modules will be competing to obtain mic from each other. And with my guess, those two modules are not developed as that way.

By Example, My modules - MMM-Hotword and MMM-AssistantMk2 both are using one mic together, but when one module is using a mic, the other should release it before. Both modules are made by me, so I can make both to work together. But I cannot think MMM-Voice and AlexaPi both could do the same thing.

maxbachmann

@Sean @richland007 yeah might be true did not test that ;)
Although I still have no clue why to use two in the first place. I mean when you decide to use Alexa Pi because privacy is no big deal for you then why use a different one for MM2 that might be a decent solution but definetly has it’s drawbacks. Can’t see much sence in taking the drawbacks of alexa in terms of privacy and then not even use the advantages :smiling_face_with_open_mouth_cold_sweat:
Whatever if you really want to have two different running with one mic you might want to consider doing it similar to @Sean by using a separate program running all the time catching the different hotwords, that call the two voice recognitions depending on the hotword

richland007

@maxbachmann AlexaPi has no control over Magic Mirror… as far as i know… it is just an Amazon Alexa on a Rpi instead of an Echo (why should i buy an Echo for the bathroom when i have the mirror).
The only integration/connection to MM is that it displays the status of Listening, Answering etc. While the reason i want MMM-voice, is to “control” the Magic Mirror… hide modules, show modules etc etc.

There is no consideration or worries as far as privacy, cloud or whatever … we all know how to live with NSA present at home one way or another…some time even with the much larger PLA … LMAO :grinning_face_with_smiling_eyes: :grinning_face_with_smiling_eyes: :grinning_face_with_smiling_eyes:

I have no idea what these other, separate programs for catching hotwords are … any pointers

D

maxbachmann

@richland007 I thought you want to run two voice assistants from the same device given you want to use the same mic and the same pi right?
Because now it seems like you want to have alexa in other rooms and mmm-voice for the bathroom ;)
Yes for Alexa you would need to write a module that receives the messages and then just hides the modules accordingly. I am just not sure what exactly you want now.
(never used Alexa, but as far as I know they have some kind of skills aswell you can easily program. Then you just need to write a short module for MM2 that receives those messages and hides/shows the specific modules ;))
For catching wakewords a good offline recognition should be snowboy. Just give it two different hotwords and whenever one is recognised you can directly activate the SST (speech to text engine) of the corresponding voice recognition which for example in case of Sean would be MM-AssistantMk2. (Never used his voice recognition. MMM-Hotword should be a good start it uses snowboy so it should be easy to use it with two hotwords (but @Sean should be able to help you more with his code, since I neither use one of the snowboy/pocketsphinx nor any online voice recongition like alexa. My current offline voice system (currently implementing it to MM2) is snips.).

Btw on the privacy side: yes the big bad NSA is everywhere, but I rather make it hard for them to get my data. When they have to attack my custom stuff at home thats absolutely possible, but still harder then them going to amazon/google and telling them to just give the data out. Second thing is companies like google/amazon I absolutely don’t want to know that private things about me. And we all know that although they claim to respect the privacy, your never sure especially since they already abused the trust before. And last but not least there are criminals that might try to abuse the data for example by catching the data while you want to transfer them to amazon/google or back. So while a offline solution might (as long as you give it internet) not be 100% secure and private, but still a lot more private than having them online. Just make getting your data harder then what they are worth for the attacker. Well enough on that guess thats a whole different topic and in the end it’s your choice anyways Lmao :rolling_on_the_floor_laughing: