brianstorms

« Previous | Next »

Google's YouTube Speech Transcription... Not Quite Ready for Prime Time

It's fun and sometimes funny to watch Google struggle to transcribe, through automated means, the spoken audio on a YouTube video.

I watched this video of Jeff Daniels reciting the Gettysburg Address and found that Google did okay, perhaps 90% right. But 90% right is still enough to get you in big trouble.

Here is the exact transcript, compared to the actual speech. I've added periods to the end of sentences and capitalized the first letter of the first word of the following sentence but otherwise, it's as is:

Google Transcription Actual Text
Forestall or in seven years ago Four score and seven years ago
our fathers brought forth on this continent a new nation our fathers brought forth upon this continent a new nation
conceived in liberty conceived in liberty
and dedicated to the proposition that all men are created. and dedicated to the proposition that all men are created equal.
Now we are engaged in a great civil war Now we are engaged in a great civil war
testing whether that nation testing whether that nation
or any nation so conceived and so dedicated or any nation so conceived and so dedicated
can lock on the door. can long endure.
We are met on a great battlefield of that war. We are met on a great battlefield of that war.
We have come to dedicate a portion of that field as a final resting place We have come to dedicate a portion of that field as a final resting place
for those who here gave their lives that that nation might live. for those who here gave their lives that this nation might live.
It is altogether fitting and proper It is altogether fitting and proper
the we should do this. that we should do this.
But in a larger sense But in a larger sense
we cannot dedicate we cannot dedicate
we cannot concentrate we cannot consecrate
we cannot hal all this ground. we cannot hallow this ground.
The brave man The brave men
living and dad who struggled here living and dead who struggled here
have consecrated it have consecrated it
far above our poor power to add or detract. far above our poor power to add or detract.
Both will little note nor long remember what we say here The world will little note nor long remember what we say here
but it can never forget what they did here. but it can never forget what they did here.
it is for us the living It is for us the living
rather to be dedicated here to the unfinished work rather to be dedicated here to the unfinished work
which they who fought here have thus which they who fought here have thus
far so nobly advanced far so nobly advanced.
It is rather for us to be here It is rather for us to be here
dedicated to the great task remaining before us dedicated to the great task remaining before us
that from these honored dead that from these honored dead
we take increased devotion to that cause for we take increased devotion to that cause for
which they gave the last full measure of devotion. which they gave the last full measure of devotion.
That we hear highly resolve that these dead shall not have died in vain That we here highly resolve that these dead shall not have died in vain
that this nation under God that this nation under God
still have a new birth of freedom shall have a new birth of freedom
and that government of the people and that government of the people
by the people by the people
four help people for the people
John nor perish shall not perish
from the air. from this Earth.

Not bad, but not quite there yet.

Thinking of posting a comment to this blog entry? That's nice. But please note: As of January 19. 2014, I no longer review comments. So they will never appear. So don't bother. If you want to comment on something you read here, go to twitter and write your comment there and just include "@brianstorms" in the tweet. I am no longer moderating the comments here; I just assume everything is spam and Intense Debate seems to have abandoned support for its product.

« Previous | Next »