digiBlitz, a digital Liquid Asset creation & Trading Platform

  • #2298 (no title)
  • About
    • About Us
    • Leadership
    • Roadmap
    • Investors
  • Platform
    • digiBlitz Platform Overview
  • Use Cases
    • Energy
    • Mobility
    • Urban & Rural Transformation
    • Banking and Finance
    • Manufacturing
    • Healthcare
    • Farming
    • Retail
    • Pharma and Lifesciences
  • Partners
  • Events
    • Certification Training
    • Workshop
    • Webinar
  • Innovation Lab
  • Public Network
  • Contact Us
You are at :Home»Life Science»Soon We Won’t Be Able to Tell the Difference Between AI and a Human Voice
Soon We Won’t Be Able to Tell the Difference Between AI and a Human Voice

Soon We Won’t Be Able to Tell the Difference Between AI and a Human Voice

digiblitzmedia 06 Jan 2018 Life Science Leave a comment 1237 Views

2
SHARES
ShareTweet
Click here to view original web page at futurism.com

The Voice of AI

Using their DeepMind artificial intelligence (AI), Google’s Alphabet AI research lab developed a synthetic speech system called WaveNet back in 2016. The system runs on an artificial neural network that’s capable of speech samples at an ostensibly better quality than other technologies like it. The voice of AI is becoming more human-like, so to speak. WaveNet has since been improved to work well enough for Google Assistant across all platforms.

Now, WaveNet has gotten even better at sounding more human.

In a still-to-be-peer-reviewed paper published by Google in January 2018, WaveNet is getting a text-to-speech system called Tacotron 2. Effectively the second generation of Google’s synthetic speech AI, the new system combines the deep neural networks of Tacotron 2 with WaveNet.

First, Tacotron 2 translates text into a visual representation of audio frequencies over time, called a spectogram. This is then fed into WaveNet, which reads the spectogram and creates a chart with the corresponding audio elements.

According to the study, the “model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech.” Simply put, it sounds very much like a person speaking.

In fact, Google put recordings of a human and their new AI side-by-side, and it’s difficult to tell which is the person and which is the machine.

Here’s a sample.

Synthetic Speech System

To date, AI systems have gotten better at blurring the line between human and machine. There are now AIs capable of generating images of human beings that aren’t real, but look it. Another AI can even make fake videos. One can’t also discount the fact that some AIs are getting better at storytelling, or making art.

Mimicking human speech was always a challenge for AI networks. Now, DeepMind’s WaveNet and Tacotron 2 seem to be changing that, and at quite an impressive rate. Not only does the AI pronounce words clearly, but it seems to be able to handle difficult to pronounce words or names, as well as put emphasis on the appropriate words based on punctuations. Listen in.

This isn’t to say that the new AI system is perfect, however. Its current iteration has only been trained to use one voice, which Google recorded from a woman they hired. For the WaveNet and Tacotron 2 system to work using other voices — say a male’s or another female — the system would have to be trained again.

Apart from having immediate applications for Google Assistant, as soon as the Tacotron 2 system is perfected, the technology could assume other roles. Perhaps it could even take over certain jobs, adding to the already long list of occupations that seem ripe for AI.

Click here to view original web page at futurism.com

2018-01-06
digiblitzmedia
Twitter Facebook Google + Stumble linkedin Pinterest More
Previous Article :

Ch-Ch-Changes: Software Predictions for 2018 and Beyond

Next Article :

CES 2018: Delivery Robots are Full-Time Employees at a Las Vegas Hotel

Related Articles

Oradea’s plan to become Romania’s first smart city

Oradea’s plan to become Romania’s first smart city

digiblitzmedia 29 Sep 2017
The Effect of the Internet of Things on Sustainability

The Effect of the Internet of Things on Sustainability

digiblitzmedia 26 Jan 2018
IoT Needs Qualitative User Research

IoT Needs Qualitative User Research

digiblitzmedia 16 Sep 2017

Leave a Reply Cancel reply

You must be logged in to post a comment.

Connect with:
Facebook Google Twitter

Recent Posts

The Algorithmic Colonization of Africa- Abeba Birhane
Business

The Algorithmic Colonization of Africa- Abeba Birhane

26 Sep 2019

Turn around a stalled oil and gas digital transformation | McKinsey

24 Apr 2019

The future of electricity rate design | McKinsey

16 Mar 2019

Bank of Thailand Announces ‘Milestone’ Digital Currency Project Using R3 Corda Platform

22 Aug 2018

Blockchain Xenophobia

31 Jul 2018

Newsletter

  • Careers
  • Help
  • Request Demo

Categories

Recent Comments

  • cefuroxime without a prescription on Fusce vitae nibh sit amet nulla cursus laoreet.
  • clonidinemg uk on Fusce vitae nibh sit amet nulla cursus laoreet.
  • buspirone 10mg otc on Fusce vitae nibh sit amet nulla cursus laoreet.
  • how to purchase olmesartan 20 mg on Fusce vitae nibh sit amet nulla cursus laoreet.
  • dutasteride price on Fusce vitae nibh sit amet nulla cursus laoreet.

Advertisement

Copyright 2019, All Rights Reserved
digiBlitz