How to set up windows speech recognition macros on Windows 10?

I’ve read that in the past Windows offered Windows Speech Recognition Macros as a standalone program. However, currently, this only seems to be available through shady third party sites and I can find no definite information about its existence on the official website. The only thing available on my computer is the vanilla Windows Speech Recognition, which does not contain the option to create macros.

voice recognition – How do I add new text to speech entries using Gboard?

I was using SwiftKey prior to this but I switched over to Gboard because it has better voice recognition when using speech to text. Something got changed in SwiftKey recently and the quality of speech-to-text went down significantly. But with SwiftKey I was able to correct words that I dictated and I thought that that improved the speech-to-text algorithms.

With Gboard there’s no option to correct a word so I can’t improve the speech to text recognition. Does this option exist and I can’t find it?

google maps – How to add a word to the Voice Typing recognition list?

I need to frequently say the word “olivette”. I added it to my keyboard dictionary. Voice Typing ALWAYS interprets it as “all of that”. It doesn’t learn from my correcting it.

A Google search reveals ways you USED to be able to add words to your phone’s recognition list. Other services let you (e.g. dragon).

How do you do it on Android 8.0 and later? (I’m using a motorola z-play)

design patterns – Non-specificity of voice recognition for voice assistance devices or features

I remember from quite some time ago when Siri was first launched that there was no specific way of getting the voice-triggered assistant to recognize specific voices.

These days there are many different home assistant devices like Amazon Alex and Google Home, and some information is provided in terms of setting up voice profiles and training it to recognize different voices through linking of accounts.

However, I wonder if there is a specific reason why the user experience of setting up voice recognition isn’t as easy as other biometric information like finger print or facial recognition. Is this because the technology isn’t as mature or that people don’t use it as much as other types of biometric?

Are there good examples of design patterns for enabling better specificity of voice recognition where voice control is the dominant way of interacting with a system/application?

How to unlock with face recognition for multiple users?

We are using our tablet together with my wife. I have added another user profile to the Android tablet (Samsung Tab A7, Android 10). I have switched to her account and we added her face for the recognition.

Question: is there a way to directly unlock the device with either of our faces? Otherwise the experience is awful. I need to turn on the device, click on the profile icon on the top right, catch the correct user in 1 second (otherwise screen turns off), then do the face recognition.

python – Gtk Warning Theme parsing error, trying to do some facial recognition

i’m having what i think is a gtk error in python while trying to recognize some faces and then apply a gaussian blur, i’m new in python! Here is the error:

*Gtk-WARNING *: 00:11:03.559: Theme parsing error: gtk.css:6321:10: “height” is not a valid property name

i’m currently using Archlinux and python 3+, i checked ~/.config and my Gtk is 2.0, idk if that is the issue and i also don’t know how to change it/ update it.

Here is the code i’m triying to compile:

from skimage.filters import gaussian
from skimage import color
from skimage import data

import scipy.misc
import os
import sys
import plots
import matplotlib.pyplot as plt
from PIL import Image
path = "/home/carlos/python/img/jaja.jpeg"
img = plt.imread("/home/carlos/python/img/girl.jpeg")
#plt.show(img)
trained_file = data.lbp_frontal_face_cascade_filename()

detector = Cascade(trained_file)

detected = detector.detect_multi_scale(img=img, scale_factor=1.2, step_ratio=1, min_size=(50,50), max_size=(200,200))

print(detected)

How do you socialize online and avoid facial recognition and other privacy breaching-tactics

What are some techniques to socialize online, while still maintaining privacy, specifically avoiding facial recognition? The main goal here is to make it to where only humans can recognize/track you, while making it to where computers cannot analyze and mass track you.

For example, many social media sites and dating sites require that you upload a profile picture. While you can put something completely random (like a dog or soda can), it may come off creepy or maybe make people might not want to connect with you. I would like to know if there are any balanced options between anonymity, showing your real face, not being creepy, and socially connecting with people (through imagery of your face/body).

Perhaps techniques of taking a face profile picture and using software editing to blur, distort, or stretch the image. That, or do physical scene manipulations like a shadow effect, zooming, light effect, glass, water, gas, etc., or adjusting the camera.

python – Looking for best Text annotation tool for Named entity recognition?

I was trying to annotate a text for name entity recognition model using Spacy in Python. and i had tried with Tagtog tool to annotate my text but the output in Json format look like below
text that I need to annotate,Example:-
“I like London and Berlin”
output annotation
_———————————————————————-
{“annotatable”:{“parts”:(“s1v1″)},”anncomplete”:false,”sources”:(),”metas”:{},”entities”:({“classId”:”e_1″,”part”:”s1v1″,”offsets”:({“start”:7,”text”:”London”}),”coordinates”:(),”confidence”:{“state”:”pre-added”,”who”:(“user:Antie”),”prob”:1},”fields”:{},”normalizations”:{}},{“classId”:”e_1″,”part”:”s1v1″,”offsets”:({“start”:18,”text”:”Berlin”}),”coordinates”:(),”confidence”:{“state”:”pre-added”,”who”:(“user:Antie”),”prob”:1},”fields”:{},”normalizations”:{}}),”relations”:()}
———————-‐———————————————————————-
but this output couldn’t be acceptable during training the model in python using Spacy.
I need the output looks like below format
(“I like London and Berlin.”,{entities ((7,13,”Loc”),(18,24 “Loc”))})
which annotation tool would you recommend me to get a such formatted output ?

python – Text annotation tool for Name entity recognition

i was trying to annotate a text for name entity recognition model using Spacy. and i had tried with Tagtog tool to annotate my text but the output in Json format look like below
_———————————————————————-
{“annotatable”:{“parts”:(“s1v1″)},”anncomplete”:false,”sources”:(),”metas”:{},”entities”:({“classId”:”e_1″,”part”:”s1v1″,”offsets”:({“start”:7,”text”:”London”}),”coordinates”:(),”confidence”:{“state”:”pre-added”,”who”:(“user:Antie”),”prob”:1},”fields”:{},”normalizations”:{}},{“classId”:”e_1″,”part”:”s1v1″,”offsets”:({“start”:18,”text”:”Berlin”}),”coordinates”:(),”confidence”:{“state”:”pre-added”,”who”:(“user:Antie”),”prob”:1},”fields”:{},”normalizations”:{}}),”relations”:()}
———————-‐———————————————————————-
but this output couldn’t be acceptable during training the model
i need the output looks like below format
(“I like London and Berlin.”,{entities ((7,13,”Loc”),(18,24 “Loc”))})
which annotation tool would you recommend me to get a such formatted output ?
Am Waiting Your Reply Eagerly.
Thank you God Bless You !!

websocket – how to send an image from a phone to PC(Python) in order to conduct image recognition on it then return the result back?

note I created the app with appinvetor therefore I can not adjust a code, I tried this piece of code
”’ import socket
import struct
from PIL import Image

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.bind(('0.0.0.0', 19997))
s.listen(1000)

print('Waiting for data...')

client, addr = s.accept()
print('got connected from', addr)

 buf = b''            # this caused an error, I added a b so it would be read as bytes and not      string
while len(buf)<4:
buf += client.recv(4-len(buf))
size = struct.unpack('!i', buf)
print("receiving %s bytes" % size)

with open('tst.jpg', 'wb') as img:
while True:
    data = client.recv(1024)
    if not data:
        break
    img.write(data)
print('received image')'''