Slashdot Mirror
Google Launches More Realistic Text-To-Speech Service Powered By DeepMind's AI (theverge.com)
Google is launching a new AI voice synthesizer, named Cloud Text-to-Speech, that will be available for any developer or business that needs voice synthesis on tap, whether that's for an app, website, or virtual assistant. The Cloud Text-to-Speech service is being powered by WaveNet, software created by Google's UK-based AI subsidiary DeepMind. The Verge explains why this is significant: First, ever since Google bought DeepMind in 2014, it's been exploring ways to turn the company's AI talent into tangible products. So far, this has meant using DeepMind's algorithms to reduce electricity costs in Google's data centers by 40 percent and DeepMind's forays into health care. But, directly integrating WaveNet into its cloud service is arguably more significant, especially as Google tries to win cloud business away from Amazon and Microsoft, presenting its AI skills as its differentiating factor. Second, DeepMind's AI voice synthesis tech is some of the most advanced and realistic in the business. Most voice synthesizers (including Apple's Siri) use what's called concatenative synthesis, in which a program stores individual syllables -- sounds such as "ba," "sht," and "oo" -- and pieces them together on the fly to form words and sentences. This method has gotten pretty good over the years, but it still sounds stilted.
WaveNet, by comparison, uses machine learning to generate audio from scratch. It actually analyzes the waveforms from a huge database of human speech and re-creates them at a rate of 24,000 samples per second. The end result includes voices with subtleties like lip smacks and accents. When Google first unveiled WaveNet in 2016, it was far too computationally intensive to work outside of research environments, but it's since been slimmed down significantly, showing a clear pipeline from research to product. The Verge has embedded some samples in their report to see how WaveNet sounds.
WaveNet, by comparison, uses machine learning to generate audio from scratch. It actually analyzes the waveforms from a huge database of human speech and re-creates them at a rate of 24,000 samples per second. The end result includes voices with subtleties like lip smacks and accents. When Google first unveiled WaveNet in 2016, it was far too computationally intensive to work outside of research environments, but it's since been slimmed down significantly, showing a clear pipeline from research to product. The Verge has embedded some samples in their report to see how WaveNet sounds.
No one with good sense is going to use ( and become dependent on ) a service Google provides, because Google has a long and dishonorable history of abruptly killing off products.
Add to the above that Google will be recording and mining everything you say, and if you still think it's a good idea to use their stuff, you deserve no more sympathy than the sheep who used Facebook.
Given Google's history of taking things away, I would not build anything that depends on this. It will probably disappear in a year.
Too expensive for me.
Am I missing something?
Has anyone played around with this?
The demo takes SSML, but it does not appear to support <prosody> functionality :-(
Hopefully, the Tech Awakening we're experiencing in the US at a consumer level might trickle upwards into actual products as well.
No way in hell I'm going to rely on something I have to use a remote service for, which is no doubt collecting and storing as many bits of data as possible. I don't need human-sounding-voice *that* badly that I can't wait for someone to figure out how to get 95% of this does and run on a few cores, or perhaps spare GPU capacity.
Hire a Linux system administrator, systems engineer,
These voices are quite a far cry from the results of the original wavenet paper. I suppose a lot of computational tradeoffs happened, but these are Siri-level, not human level.
This will be very useful, to telemarketers.
Personally, I'd go for the Terminator
I'm sorry Dave. I'm afraid I can't do that.
Lips smack when cocks get suck
I'll finally figure out how to pronounce 'doge'.
Have gnu, will travel.
having the ability to do this.
So what took Google so long?
Why doesn't google use all that fancy AI talent in translating text numbers in Chinese into text numbers in English. I can't believe it's all that hard to do yet they fail all the time.
If it ain't Majel Barrett, it ain't shit.
The Verge has embedded some samples in their report to hear how WaveNet sounds.
and doesn't have to rely on the cloud to work, then, Maybe, I might work with it. Otherwise my voice patterns are in the cloud and subject to data breaches. That's as bad as actually putting your signature on an electronic signature pad.
The NSA does speech to text so they can collect all voice calls and index them for textsearch and trigger words. THis is about text to speech.
If you check the competitor voice generation in the article it's also pretty good. Things have improved since Radiohead's depressing song 'Fitter Happier'
https://www.youtube.com/watch?...
Why 'cloud' when local works well?
$ sudo aptitude install libttspico-utils
$ pico2wave -w h.wav "Hello World"
$ aplay h.wav
2bits.com, Inc: Drupal, WordPress, and LAMP performance tuning.