Google DeepMind gets closer to sounding human

Researchers at DeepMind use WaveNet AI to mimic human speech

Artificial intelligence researchers at DeepMind have created some of the most realistic sounding human-like speech, using neural networks.

Dubbed WaveNet, the AI promises significant improvements to computer-generated speech, and could eventually be used in digital personal assistants such as Siri, Cortana and Amazon's Alexa.

The technology generates voices by sampling real human speech from both English and Mandarin speakers. In tests, the WaveNet generated speech was found to be more realistic than other forms of text-to-speech programs but still falling short of being truly convincing.

In 500 blind tests, respondents were asked to judge sample sentences on a scale of one to five (five being most realistic). WaveNet was rated 4.21 in English and 4.08 in Mandarin (actual human speech was rated 4.55 in English and 4.21 in Mandarin in the tests). That side, WaveNet managed to outperform other speech methods.

Advertisement
Advertisement - Article continues below
Advertisement - Article continues below

While other artificial speech generators focus on language, WaveNet targets the sound waves being produced, analysing raw audio signal waveforms and modelling speech on that. The researchers also used the same technique to produce music after listening to piano solos on YouTube.

"WaveNets open up a lot of possibilities for TTS, music generation and audio modelling in general. The fact that directly generating timestep per timestep with deep neural networks works at all for 16kHz audio is really surprising, let alone that it outperforms state-of-the-art TTS systems. We are excited to see what we can do with them next," said Deepmind in a blog post.

Deepmind has also published a paper that goes into much more detail on the technology.

The research outfit was also responsible for creating an AI system to beat a champion Go player this year.

Featured Resources

What you need to know about migrating to SAP S/4HANA

Factors to assess how and when to begin migration

Download now

Your enterprise cloud solutions guide

Infrastructure designed to meet your company's IT needs for next-generation cloud applications

Download now

Testing for compliance just became easier

How you can use technology to ensure compliance in your organisation

Download now

Best practices for implementing security awareness training

How to develop a security awareness programme that will actually change behaviour

Download now
Advertisement

Most Popular

Visit/policy-legislation/data-governance/354496/brexit-security-talks-under-threat-after-uk-accused-of
data governance

Brexit security talks under threat after UK accused of illegally copying Schengen data

10 Jan 2020
Visit/security/cyber-security/354468/if-not-passwords-then-what
cyber security

If not passwords then what?

8 Jan 2020
Visit/policy-legislation/31772/gdpr-and-brexit-how-will-one-affect-the-other
Policy & legislation

GDPR and Brexit: How will one affect the other?

9 Jan 2020
Visit/web-browser/30394/what-is-http-error-503-and-how-do-you-fix-it
web browser

What is HTTP error 503 and how do you fix it?

7 Jan 2020