My Final Year Project used robotics, speech recognition, body mapping and it was possibly the coolest thing I've ever done. I did it to be balls out ambitious as I wanted an impressive project to help me get a job...

Sweet, my motivation for coding my personal projects has started to come back.

Last night I setup my Personal Assistant project with Text to speech and Voice recognition.

Now I just have to get it to react to commands.

I'm new to speech recognition game, so I was wondering what's the advantage of Tensorflow's audio recognition over Microsoft.Speech in Visual studio, if any.
Also open to any other suggestions/lectures on the matter.

Google bloody captcha.

It works fine, until you have more than one form on a page then the complexity increases by 100000%.

Finally my colleague gets it working then I read an article that says bots use Google own speech recognition service to defeat it. Fun times.

IPhone speech to text has come a long way. Definitely has improved. Real-time dictation rather than batching it.

I am currently doing approximately 50 percent of my rants by voice. In fact the rank you are reading I did by voice.

You can easily do punctuation such as a period, new paragraph, new line, caps and lower case. The speech recognition is excellent even with my New York accent and it learns the more you use it. Rarely does it get a word wrong.

Editing still has to be done manually and is a pain but that may change as dragon already allows you to do in-line editing. iOS speech to text has already surpassed dragon in some facets.

I do have to press the add new and post buttons at this Time to post my rants. But that may change as the enhanced dictation on the map allows you access to specific commands.

I will keep you informed of progress and I will be testing on android over the next few days as well.

Eavesdropping by phone's microphone and speech recognition to serve targetted ads by Google? Anyone here had a feeling this happened to them or knows is this already a thing?

Happened to me on my Android phone multiple times over last year on different subjects, that I was talking live with a person, for example how someone had eyelid surgery (my phone was locked in my pocket the whole time and I didn't google search what that is, or made any text input into device whatsoever) and couple minutes later an ad came on my phone for exactly something we were discussing before. Weird coincedence or something more? 🤔

Hey

Anyone looking into how A.I. can improve language learning courses (and obviously, speech recognition) and such?

I know, A.I. buzzword, but I think it's applicable here..

Who is actually coding A.I. right now anyway? anyone?

Here is a personal project I've been working on lately. It's not public, but just wanted to share. It's a custom chatbot I created using a LAMP stack. Its built on top of a framework called Program-O to handle the knowledgebase storage and processing along with some basic NLP. I added the web speech api functionality myself so it supports recognition as well as speech synthesis. Anyways, pretty proud of this one.

I used speech recognition package of python in one of my projects. It is working properly but it is not recognising some words, like if I say my name so it will print something else, printing 2 as doose, 1 as drone. To sum up, it's not considering few words.
I tried some amendments like set the language to english-india.
language =en-IN
But after this also, same problem arose.

Someone has to start manufacturing quality HUD glasses...
Imagine the possibilities and comfort...
no more neckpain from crouching above your laptop/tablet/smartphone, imagine the navigation systems, imagine you could read messages, articles, code, watch videos whatever you are doing, even work on your code with some kind of keyboard (or with speech recognition)
I want this soo bad..

me "text someone"

console "Google Speech Recognition thinks you said 'ketamine'!"

Having hard time to make my friend understand that you don't need to build everything from scratch and we can get started for free with commercial solutions for speech recognition and only pay when we have a decent userbase. The worst part is he doesn't believe it even when it is clearly written on the website.

May I know the best python open source framework to develop speech recognition from scratch

I'm doing this internship because I'm a self taught programmer and I want to land a job at this obviously. Well I get this boss that first asks me for a chatbot. I'm a bit overwhelmed but decided to take it because didn't seem that complicated just time consuming. Then he goes and scale the chatbot to a full blown A.I. that talks, has a avatar reacting to emotions, has speech recognition and a lot of things. I been making progress on the normal bots you see around messenger and slack. I asked for more people to work for me and there is a guy who is working back-end and has never sit down and taught me his system even do I ask everyday for it. Seems like this internship is a waste of time. Any tips?

How can you make a login form in which details are filled via voice? One way is that we can use pyauto gui for fetching coordinates but it's not working as per my wish...

Guys does anyone use background recording library or SDK on Cordova in which it does an automatic speech recognition other than sphinx because till now sphinx has 0 accuracy and found out it's a very bad

Hey, what is the best way to add speech recognition on web? Did web developers have python developer like AI/ML technology.