MMM-voice

strawberry 3.141

@dmwilsonkc if you run your mycroft core from the node helper as i do with pocketsphinx in voice then there is no need at all to mess with the socket server

dmwilsonkc

@strawberry-3.141 I didn’t realize that was a possibility. I currently start Mycroft when the pi boots up in a virtualenv as was recommended by the mycroft folks. Both the MM and Mycroft run exactly as they should. The only exception is the microphone issue- not being able to access the microphone from two processes at the same time. I have no idea how I would start Mycroft from the node_helper.js.

At this point I am very confused on the best way to go. To me, it seems like the socket communication between two concurrently running processes would be easier. But you are the expert.

Any advice you suggest would be welcomed. Thanks again.

ime90

Hi everyone. I’m having trouble with my voice module.

It doesn’t seem to register any of my commands. The microphone icon is blinking but whenever I say “hide modules” or any other command it doesn’t register it.

In the terminal it says “Starting pocketsphinx.” Don’t know it that is of any concerns? If anybody has any tips they are more than welcome.

strawberry 3.141

@ime90 can you check the .lm and .dic files in your module folder and see if they are empty or include your commands

ime90

@strawberry-3.141 hi strawberry, thanks for the response.

I’ve managed to make it work, but the problem is that the operations were uuuuultra slow.

I’ve timed the response time in 10 different occurrences.

After saying “MAGIC MIRROR” it takes an average of 7 seconds for the microphone icon to start blinking.

After saying “HIDE” it takes an average of 15 second (hope this isn’t normal) to hide the modules.

Is this due to my RPI3? Any and all tips and experiences are welcome.

dmwilsonkc

@ime90 I am running MMM-voice on a RPi3b and while it is not as fast as my Mycroft-core in responding to its wake word, it is much faster than the times you have stated. I turned the debug = true so that I could see what it is doing. I would say the times you have stated are at least double what it takes MMM-voice on my Pi. I changed my wake word to Hey Jarvis. I don’t know if that made any difference in how fast it recognizes the wake word. I also added the Hello-Lucy modifications to the MMM-voice module. It is not “fast” in responding to commands, but it only takes a few seconds (5 to 6sec.) to Hide/Show modules if I remember right.

joe84maiden

I wrote this in a different thread not too long ago actually, but I noticed a vast increase in detection/response rate when moving from a cheap USB mic to a decent webcam microphone. I would say the response now is on the order of 1-2 secs, with effectively no errors in voice interpretation. I’m sure this is helped immensely because the clarity of the audio into the rpi is much clearer - the cheap USB mic had terribly noisy audio in.

sdetweil

i am running MMM-voice on an ODroid Xu4, which is very fast.

I also use another voice enabled smart mirror on this same device.

with a Logitech webcam as the mic.

MMM-voice gets the hotword correct every time, but almost none of the following words.

the same hardware setup works correctly with arecord as the wav source, but uses google speech detection for everything after the hotword.

it appears the system is using the default language model (lm) and dictation (dic) files.

anyone have a suggestion on debugging this?

strawberry 3.141

@sdetweil set debug: true in the config and you will see what the mirror recognizes

sdetweil

i have that, but the text ‘recognized’ is not what i said.

if I speak slowly, i can get ‘magic mirror’
then wake up is ‘wake go’ or ‘wake all’,

hide calendar is ‘hide who’
open help is ‘open go’

the smart-mirror project also uses ‘go to sleep’ and ‘wakeup’

‘hide newsfeed’ is ‘hide to show the’, ‘hide is the’

none of the commands, when recognized, do anything…

hide modules

go to sleep (not on PI so the tvservice doesn’t exist), but no error is logged

strawberry 3.141

@sdetweil I can tell you the same as I just told another user

as the author of MMM-voice I can tell you, that my module doesn’t support a command called hide clock at all. You are probably using hello-lucy, at least that’s a mod I’m aware of which enhances the commands. You can see the command list here https://github.com/fewieden/MMM-voice#usage

i also had problems due to my accent. you can also look into the dic file how the system expects you to pronounce it

sdetweil

ok, got it… voice detection is sensitive…

richland007

@strawberry-3-141 OK i am trying to install this module and i have read all forum posts on this thread.
I did have AlexaPi installed and working previously and as i can tell from other users this installation ruins it but i could live with that. However MMM-voice keeps giving error 1 on its error log even after deleting node modules, pocketsphinx and sphinxbase and reinstalling again. The icon on MM goes briefly Ready Select Mode than back to Error how do i fix that like i said i have read everything all installations go perfectly all 1 through 5 out of 5. what am i doing wrong??
The other question is… I also want to use 2 microphones ideally and both apps… i was using AlexaPi flawlessly with one of the mics and i wanted to use a second mic for MMM-voice since it gives you the option to select which one you want to use do you think that is doable? is it meant for that??
What can i do to use both AlexaPi and one of the MMM voice modules so i can control the display and show and hide certain modules both on the same Rpi.
I tried MMM-MirrorMirrorOnTheWall already but i am stuck half way with no one to help me through the end and it is an extremely difficult module to fully install.
Anyhow any help will be greatly appreciated
Denis

strawberry 3.141

@richland007 can you please enable temporarily the more detailed debug log with debug: true?

richland007

@strawberry-3-141 Thank you so much for replying back to me :)
Did what you asked and on the MM itself it says Error Undefined but on the debug log everything sems to go fine until the very last sentence that says this:

“Error opening audio device plughw:1 for capture: Connection refused
FATAL: “continuous.c”, line 245: Failed to open audio device”

When i run “cat /proc/asound/cards” i get this
“0 [ALSA ]: bcm2835_alsa - bcm2835 ALSA
bcm2835 ALSA
1 [Set ]: USB-Audio - USB Headphone Set
USB Headphone Set at usb-3f980000.usb-1.5, full speed”

And in the config.js file obviously i have selected the only mic i have right now number 1 USB headphone set and i know it is working just fine.

Let me know how what does that tell you
and again thank you
Denis

strawberry 3.141

@richland007 can you check the following to see if another program can access the mic https://scribles.net/voice-recording-on-raspberry-pi/

Is there already another Programm running in the background which is accessing the mic?

richland007

@strawberry-3-141 Hello there,
I tested the mics following the steps on the above site and my microphone works just fine no errors the audio is good coming from the speakers and clear i do get a warning that does not affect anything that says:
“Warning: rate is not accurate (requested = 44100Hz, got = 48000Hz)
please, try the plug plugin”
but it does not affect the audio or the command actually when i try another mic it does not give me that error at all however the audio is not nearly as good.
So to recap the mic works it records a test file and gives no errors.

D

strawberry 3.141

@richland007 it looks like it is a problem between alsa and pulseaudio https://sourceforge.net/p/cmusphinx/discussion/help/thread/c39732a2/

richland007

@strawberry-3-141 I know i have ALSA on my system but i don’t recall ever having to install Pulseaudio on my system. Is it required by this module? pulse audio that is …can i install it??
Denis

strawberry 3.141

@richland007 I’m sorry I can’t really tell you something other than what I find googling myself, I never experienced sth similar other than couldn’t open device resource is busy.