Science

British company develops artificial voice that can speak with 'deep human emotion' – and even cry 


Alexa, have a heart! British company develops artificial voice that can speak with ‘deep human emotion’ — and even cry

  • The software from Sonantic can imbue dialogue with emotional inflections
  • It works by sampling lines recorded by voice actors with different deliveries
  • Game and film companies can then use the AI to produce speech in minutes
  • The actors are given royalties every-time their synthesised voices are used 

A British company has developed an artificial voice that can speak with ‘deep human emotion’ — and even cry — with complete realism.

The digital helpers that we are used to — like Alexa and Google Assistant — tend to speak in close-to monotones, without real inflection to convey emotion.

While this may suffice for voice assistants, such flat computer-generated voices are unsuitable for applications like producing dialogue for video games or film. 

However, technology developed by the ten-person team at the London-based firm Sonantic allows the creation of authentic-sounding lines of speech in minutes.

The software can imbue its voices with various characteristics — from panic to sadness and even breathlessness.

A British company has developed an artificial voice that can speak with 'deep human emotion' — and even cry — with complete realism (stock image)

A British company has developed an artificial voice that can speak with ‘deep human emotion’ — and even cry — with complete realism (stock image)

‘We create hyper-realistic artificial voices. Unlike other text-to-speech companies, we specialise in subtleties and nuance, giving voice acting on demand, essentially,’ Sonantic chief executive Zeena Qureshi told The Times.

To create each distinct voice, the firm works with actors to record assorted words and sentences spoken with different inflections — from which the AI tool can construct any line as requested for delivery with one of various emotions. 

When a game or film production company uses one of Sonantic’s synthetic voices, the actor who helped create such is then given royalties for their contribution. 

‘Voice pipelines and entertainment work are quite heavy on logistics, such as casting, editing, directing, booking studios and doing several iterations and there is quite a lot of cost going into that,’ Ms Qureshi told The Times. 

‘We can take the process from months down to minutes and spare the hassle of all the logistics involved — and it’s cheaper,’ she added. 

One key advantage of the system over using conventional voice-actors comes when last minute dialogue changes are required.

While bringing an actor back in to re-record lines can be time-consuming — especially if conflicting schedules are involved — the AI can deliver new speech in the desired voice within mere minutes. 

‘We are using deep learning to really focus on those micro elements of, say, what constitutes sadness,’ Sonantic chief technology officer John Flynn told The Times.

‘So we have the algorithms focus on the intakes of breath and different sort of noises that would happen when someone is crying and the pitches of tone.’

According to the Times, the closure of traditional recording studios during lockdown has seen Sonantic approached by various television and film studios looking for alternative ways to secure the voice-work they require. 

WHICH SMART SPEAKER SHOULD YOU BUY?

Gadget makers are flocking to create smart speakers. 

Already Samsung has revealed plans for a Bixby speaker to take on Apple’s HomePod, Amazon’s Echo and Google’s Home.

Apple’s speaker will have a higher price tag than the Amazon Echo range, which begins at $49 (£49) for the Echo Dot.

The speaker will provide a hub for appliances via Apple’s HomeKit system and establish a centre inside the home to lock people in to using other Apple services, according to the report.

A speaker might help customers stay loyal to other services such as Apple Music, Apple Watch, Apple TV and AirPods. 

Google’s $130 (£105) Home speaker is triggered by the phrase ‘Hey Google’ while Amazon’s Echo uses ‘Alexa’.

Amazon's $50 (£40)  Echo Dot puts the firm's smart speaker in a small package

Amazon’s $50 (£40) Echo Dot puts the firm’s smart speaker in a small package

Amazon’s smart speaker is available in two versions – the full sized $180 (£145) Echo shown here, and a smaller, $50 (£40) version called the Echo Dot.

Amazon Echo uses Microsoft’s Bing search engine to provide additional information, while Google Home uses the company’s own Google Search.

Both Home and Echo are continually listening for commands, though Google and Amazon say nothing gets passed back to them until the speakers hear a keyword — ‘OK, Google’ for Home and ‘Alexa’ for Echo.

Google Home Mini:  Google's clever tech-filled $49 (£34) doughnut can do almost everything  its bigger voice controlled Google Assistant powered sibling can do, including answer questions and control third-party devices.

Google Home Mini:  Google’s clever tech-filled $49 (£34) doughnut can do almosteverything  its bigger voice controlledGoogle Assistant poweredsibling can do,including answer questionsand control third-party devices.

Google’s Assistant software is also able to answer follow-up questions on the same topic, in a near-conversation style, but Echo as yet cannot.

However, Amazon’s Alexa software has a wider range of skills on offer that enable it to link up with and control more third-party devices around the home.

A light comes on to remind you that it’s listening.

You can turn off the microphone temporarily, too. 



READ SOURCE

Leave a Reply

This website uses cookies. By continuing to use this site, you accept our use of cookies.