Software Translates Your Voice into Another Language
54 replies, posted
[release][b]Researchers at Microsoft have made software that can learn the sound of your voice, and then use it to speak a language that you don't. The system could be used to make language tutoring software more personal, or to make tools for travelers.
In a demonstration at Microsoft's Redmond, Washington, campus on Tuesday, Microsoft research scientist Frank Soong showed how his software could read out text in Spanish using the voice of his boss, Rick Rashid, who leads Microsoft's research efforts. In a second demonstration, Soong used his software to grant Craig Mundie, Microsoft's chief research and strategy officer, the ability to speak Mandarin.[/b]
Hear Rick Rashid's voice in his native language and then translated into several other languages:
English: [url]http://www.technologyreview.com/files/82520/100006.ogg[/url]
Spanish: [url]http://www.technologyreview.com/files/82523/rick_mx_00000.ogg[/url]
Italian: [url]http://www.technologyreview.com/files/82521/rick_it_new.ogg[/url]
Mandarin: [url]http://www.technologyreview.com/files/82522/rick_mandarin.ogg[/url]
In English, a synthetic version of Mundie's voice welcomed the audience to an open day held by Microsoft Research, concluding, "With the help of this system, now I can speak Mandarin." The phrase was repeated in Mandarin Chinese, in what was still recognizably Mundie's voice.
"We will be able to do quite a few scenario applications," said Soong, who created the system with colleagues at Microsoft Research Asia, the company's second largest research lab, in Beijing, China.
"For a monolingual speaker traveling in a foreign country, we'll do speech recognition followed by translation, followed by the final text to speech output [in] a different language, but still in his own voice," said Soong.
The new technique could also be used to help students learn a language, said Soong. Providing sample foreign phrases in a person's own voice could be encouraging, or easier to imitate. Soong also showed how his new system could improve a navigational directions phone app, allowing a stock synthetic English voice to seamlessly read out text written on Chinese road signs as it relayed instructions for a route in Beijing.
The system needs around an hour of training to develop a model able to read out any text in a person's own voice. That model is converted into one able to read out text in another language by comparing it with a stock text-to-speech model for the target language. Individual sounds used by the first model to build up words using a person's voice in his or her own language are carefully tweaked to give the new text-to-speech model a full ability to sound out phrases in the second language.
Source: [url]http://www.technologyreview.com/computing/39885/[/url][/release]
Looks like Microsoft Research is on a roll this week.
Sounds like it could potentially be very useful, especially for those traveling or even talking to someone else over the Internet
though it still sounds pretty synthesized
Best hopes for the people who make a living translating business conferences for international corporations.
Name it Babblefish
Is the voice detection as bad as youtube's auto caption? Bad voice recognition + engrish translation...
This sounds really promising, although I can't check the integrity of the translations.
Aren't there already devices like these? They look like a little phone that you hold that automatically translates languages for you. It's been out for a few years now.
[QUOTE=Zillamaster55;35093068]Name it Babblefish[/QUOTE]
I'd prefer Babelfish
What about languages with completely different sentence structures? Or with words that may not translate to anything or translate to multiple things (a common problem with all text based translation software)?
[QUOTE=AceOfDivine;35093117]Is the voice detection as bad as youtube's auto caption? Bad voice recognition + engrish translation...[/QUOTE]
Voice detection currently is way more advanced than youtube's. Check out all the VR software for android devices, hell, I think they have voice search built in and it's fucking great.
So now you can translate English sentences to Japanese and back again to make them nonsense... and hear it?
[QUOTE=teh pirate;35093053][img]http://4.bp.blogspot.com/-EC8fL_gcjGM/TjAsr35qhhI/AAAAAAAABC8/SfmVnsOzMok/s1600/mass_effect_logo_lg-580x167.jpg[/img][/QUOTE]
I'm sorry, can you repeat that in Galactic?
[QUOTE=mr apple;35093128]Aren't there already devices like these? They look like a little phone that you hold that automatically translates languages for you. It's been out for a few years now.[/QUOTE]
They require you to type in what you want to say in English (or whatever your native language might happen to be). You can't have a conversation with one because it doesn't translate back.
With this you could in theory have a device sitting on a table and two people speaking their native languages would be able to communicate.
[QUOTE=Jsm;35093155]They require you to type in what you want to say in English (or whatever your native language might happen to be). You can't have a conversation with one because it doesn't translate back.
With this you could in theory have a device sitting on a table and two people speaking their native languages would be able to communicate.[/QUOTE]
I remember seeing a video of it, 2 guys each had one and it translated when spoken into
Edit, doesn't really matter that much, can't really remember it too well.
But google translate already does all that.
Am i missing something here?
[QUOTE=teh pirate;35093053][img]http://4.bp.blogspot.com/-EC8fL_gcjGM/TjAsr35qhhI/AAAAAAAABC8/SfmVnsOzMok/s1600/mass_effect_logo_lg-580x167.jpg[/img][/QUOTE]
Is it a bad thing if this was the first thing I thought of?
Microsofts been hitting the news all week! wow, this seems cool.
Translation still has some way to go, especially since its very hard to take context into account, and many languages have different rules that apply to different situations, as well as words that simply cant be translated (There are no words to say it in the other language), which is a common problem with the variations of Chinese afaik.
[QUOTE=meppers;35093178]But google translate already does all that.
Am i missing something here?[/QUOTE]
You're missing that you speak into this device, and in your own voice, the device beings to speak in whatever language you selected. There's no reading of text involved.
They really need to make those phone camera based translators into a computer program.
Go into a russian server in TF2, communicate with everyone effectively, provided that you understand russian. I can understand some russian, but i can't speak it.
Now just wait for apple to ripoff the idea and try to say microsoft ripped them off.
What if you have a thick accent like me
This is really neat, think, 20 years ago, this wouldn't even have been fathomable. Incredible shit, can't wait for it to get released.
You can practice speaking your Spanish or Italian on it and see how stupid you sound.
I love how other countries spent the time to learn English and also teach it and we've just gone, fuck it lets get a computer to do it for us