Scratch should be a able to use a computer's microphone to recognize a voice. For example, a recording could say, "move right ten steps". Then when this recording is recognized, the sound it could run a script. Or you could type something in Scratch and then Scratch could recognize whether your voice is saying the text that you wrote. This would also use a computer's microphone.
Offline
this is an awesome idea
Offline
But so hard not even Bill Gates could implement it.
I don't really see this necessary though...
Offline
well there is loudness but theres no pitch so its little difficult but u can make your language with <loud?> - 0/1 ex. 111001011010110100 - pharoah 8)
Offline
Make a Sound Frequency reporter. And a (When [] said) hat block.
Offline
That would be hard!
Offline
nah
too complex
Offline
That's a great idea, but extremely hard, and I don't think it's really necessary to need. Most scratchers find putting blocks together convenient already.
Offline
waveOSBeta wrote:
Make a Sound Frequency reporter. And a (When [] said) hat block.
That would be incredibly difficult to create. I was thinking more of a pitch, loudness, and syllable sensors.
Offline
OK guys, this thread about 1.5 years old - let's just let it die, shall we?
Offline
waveOSBeta wrote:
Make a Sound Frequency reporter. And a (When [] said) hat block.
That would be incredibly difficult to create. I was thinking more of a pitch, loudness, and syllable sensors.
Offline
As a step to voice recognition:
1. When using
http://scratch.mit.edu/forums/viewtopic.php?id=17499#req_message
it will be nice to have the sound for the word as well.
2. Record microphone user input as a variable, and play it. It looks like repeating something user inputted. How about a game called "Copy Me"?
Offline
Making speech is like squeezing toothpaste out of a tube. Speech Recognition is like putting all back in. Even if it comes out, it's not like scratch would be the first to have it.
Offline
throughthefire wrote:
Making speech is like squeezing toothpaste out of a tube. Speech Recognition is like putting all back in. Even if it comes out, it's not like scratch would be the first to have it.
I already heard that phrase. Where did you take it from? Some speech tutorial?
By the way, *frown* to whoever mega bumped this post!
Offline
LS97 wrote:
throughthefire wrote:
Making speech is like squeezing toothpaste out of a tube. Speech Recognition is like putting all back in. Even if it comes out, it's not like scratch would be the first to have it.
I already heard that phrase. Where did you take it from? Some speech tutorial?
By the way, *frown* to whoever mega bumped this post!
To be honest, I don't even remember where I got it!
Offline
throughthefire wrote:
LS97 wrote:
throughthefire wrote:
Making speech is like squeezing toothpaste out of a tube. Speech Recognition is like putting all back in. Even if it comes out, it's not like scratch would be the first to have it.
I already heard that phrase. Where did you take it from? Some speech tutorial?
By the way, *frown* to whoever mega bumped this post!To be honest, I don't even remember where I got it!
Chrischb's post, I think.
"READ THIS BEFORE SUGGESTING" #9.
Offline
kayybee wrote:
throughthefire wrote:
LS97 wrote:
I already heard that phrase. Where did you take it from? Some speech tutorial?
By the way, *frown* to whoever mega bumped this post!To be honest, I don't even remember where I got it!
Chrischb's post, I think.
"READ THIS BEFORE SUGGESTING" #9.
Oh yeah!
Offline
can you use <loudness> and <sensor value [sound]>?
Offline
threepointonefour wrote:
can you use <loudness> and <sensor value [sound]>?
I think that to do that you'd need an extraordinary understanding of the English language and would certainly have to account for various accents. It might be possible, but I don't think it's plausible.
Offline
It DOES exist! Ever played "Brain training" on the DS? But it will be hard to implement in scratch
Offline
Speech recognition in Scratch is difficult because:
1) basic sampling rates need to be about 2X the highest frequency ... human speech then would need to be sampled at a minimum of about 5000 times per second.
2) on my macbook (2GHz) machine, I can get a counter to count to 42 in 1 second.
3) if you were able to store the "amplitude" or volume of each of those samples in a list you would get roughly 5000 items in a list every second.
Not trying to be a nay-sayer, but I don't think Scratch is quite the tool you want to do this kind of programming!
CHEERS
Offline