SME Times is powered by   
Search News
Just in:   • IMF urges US to cut debt, deficit  • China mulls anti-dumping measures on synthetic rubber imports  • PNB's 'Mission Gandhigiri' to help recover Rs 1,800 cr  • SA leader leaves Commonwealth summit to deal with protests  • Apple announces donation programme to mark Earth Day 
Last updated: 02 Jan, 2018  

Google.9.Thmb.jpg Google develops human-like text-to-speech AI

Google.9..jpg
   Top Stories
» Delayed GST refund to exporters: Prabhu to raise issue before FinMin
» Need to set up farming, non-farming MSMEs in NE: Giriraj
» Fiscal needs of each state will be individually assessed: N K Singh
» Indian fruit exporters eye Central Asia: APEDA Chairman
» Modi calls for stronger ties between India, Nordic countries
IANS | 02 Jan, 2018
In a major step towards its "AI first" dream, Google has developed a text-to-speech artificial intelligence (AI) system that will confuse you with its human-like articulation.

The tech giant's text-to-speech system called "Tacotron 2" delivers an AI-generated computer speech that almost matches with the voice of humans, technology news website Inc.com reported.

At Google I/O 2017 developers conference, company's Indian-origin CEO Sundar Pichai announced that the internet giant was shifting its focus from mobile-first to "AI first" and launched several products and features, including Google Lens, Smart Reply for Gmail and Google Assistant for iPhone.

According to a paper published in arXiv.org, the system first creates a spectrogram of the text, a visual representation of how the speech should sound.

That image is put through Google's existing WaveNet algorithm, which uses the image and brings AI closer than ever to indiscernibly mimicking human speech. The algorithm can easily learn different voices and even generates artificial breaths.

"Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech," the researchers were quoted as saying.

On the basis of its audio samples, Google claimed that "Tacotron 2" can detect from context the difference between the noun "desert" and the verb "desert," as well as the noun "present" and the verb "present," and alter its pronunciation accordingly.

It can place emphasis on capitalised words and apply the proper inflection when asking a question rather than making a statement, the company said in the paper.

Meanwhile, Google's engineers did not reveal much information but they left a big clue for developers to figure out how far they have come in developing this system.

According to the report, each of the '.wav' file samples has a filename containing either the term "gen" or "gt."

Based on the paper, it's highly probable that "gen" indicates speech generated by Tacotron 2 and "gt" is real human speech. ("GT" likely stands for "ground truth," a machine learning term that basically means "the real deal".)
 
Print the Page Add to Favorite
 
Share this on :
 

Please comment on this story:
 
Subject :
Message:
(Maximum 1500 characters)  Characters left 1500
Your name:
 

I loved
Lalu | Fri Jan 12 09:00:15 2018
Wetyb


 
  Customs Exchange Rates
Currency Import Export
US Dollar
66.20
64.50
UK Pound
87.50
84.65
Euro
78.25
75.65
Japanese Yen 58.85 56.85
As on 20 Apr, 2018
  Daily Poll
Is counterfeiting a major threat to SMEs?
 Yes
 No
 Can't say
  Commented Stories
» Starting an import export business: Basic guide for beginners(39)
» Startup India has created large-scale jobs: Commerce ministry(4)
» Banks need to speed up MSME loans under PMEGP: Govt(3)
» New MSME definition(2)
» Three years of Mudra(2)
 
 
About Us  |   Advertise with Us  
  Useful Links  |   Terms and Conditions  |   Disclaimer  |   Contact Us  
Follow Us : Facebook Twitter