Google's new AI is able to pick out voices in a crowd

The tech could be used for hearing aids and video conferencing

Google's Research team has developed technology to recognise individual voices in a crowd, just as a human can.

It's based on the cocktail party effect, which refers to how the human brain mutes other sounds and voices when having a conversation with an individual in a busy place. The technology works by separating a sound source into separate sound strings.

Google's demonstration study uses a video with lots of people talking at once. The user can select a particular face and they'll hear the soundtrack of just that person. They are also able to select the context of the conversation and only references to that conversation is played, even if multiple people are discussing the subject matter.

The company explained its technology could be used to improve how hearing aids work, or boost video conferencing tools, enabling them to take place in the middle of an office space, for example, rather than only in a soundproofed meeting room.

Inbar Mosseri and Oran Lang, software engineers working on the project at Google Research explained the sound goes hand in hand with the visual cues, analysing the mouth movements to match the sound with the right person.

"Intuitively, movements of a person's mouth, for example, should correlate with the sounds produced as that person is speaking, which in turn can help identify which parts of the audio correspond to that person," said researchers Inbar Mosseri and Oran Lang, writing in a blog post.

"The visual signal not only improves the speech separation quality significantly in cases of mixed speech (compared to speech separation using audio alone, as we demonstrate in our paper), but, importantly, it also associates the separated, clean speech tracks with the visible speakers in the video."

The data used to develop the technology was collated from 100,000 videos of lectures and training videos on YouTube. Parts of the speeches and lectures with no background sound and just a single person in view were then extracted to generate videos of a cocktail party type environment, with non-speech background noise obtained from AudioSet.

Google Researchers could then use this content to train a multi-stream convolutional neural network-based model to pull out individual conversations.

Google Research's findings are outlined in an in-depth report called Looking to Listen at the Cocktail Party and it explained it would be applying the principles of the technology to products in the future.

Featured Resources

Navigating the new normal: A fast guide to remote working

A smooth transition will support operations for years to come

Download now

Leading the data race

The trends driving the future of data science

Download now

How to create 1:1 customer experiences at scale

Meet the technology capable of delivering the personalisation your customers crave

Download now

How to achieve daily SAP releases

Accelerate the pace of SAP change to support your digital strategy

Download now

Recommended

MarqVision detects counterfeit products with deep learning and AI
intellectual property

MarqVision detects counterfeit products with deep learning and AI

18 Sep 2020
The IT Pro Podcast: Attack of the AI hackers
artificial intelligence (AI)

The IT Pro Podcast: Attack of the AI hackers

14 Aug 2020
MIT develops AI tech to edit outdated Wikipedia articles
artificial intelligence (AI)

MIT develops AI tech to edit outdated Wikipedia articles

13 Feb 2020

Most Popular

16 ways to speed up your laptop
Laptops

16 ways to speed up your laptop

16 Sep 2020
16 ways to speed up your laptop
Laptops

16 ways to speed up your laptop

16 Sep 2020
Windows Server flaw sparks emergency US gov warning
vulnerability

Windows Server flaw sparks emergency US gov warning

21 Sep 2020