Scientists develop AI that can flirt by using ‘non-word sounds’ such as sighs and breaths

Scientists develop AI that can flirt by using ‘non-word sounds’ such as sighs and breaths

A new artificial intelligence program has been developed that can mimic flirty speech patterns, thanks to new ‘non-word sounds’ including sighs and breaths. 

Sonantic, based in London, England, produces expressive artificial intelligence voices for a range of uses, including Hollywood movies and computer games.

The latest development was built with an ‘unnamed Hollywood client’ called ‘What’s Her Secret?’, designed to create a flirty female lead character ‘that has never lived’. 

They released a video, with the face of an actress but voice of AI, designed to demonstrate it is possible to create ‘hyper-realistic romantic encounters.’

In developing the flirty AI, the team also discovered some secrets that humans can use to sound more romantic and flirty, including slowing down to create suspense, gently smiling when speaking, and keeping a sooth, consistent pace.  

Scientists develop AI that can flirt by using ‘non-word sounds’ such as sighs and breaths

In developing the flirty ai, the team also discovered some secrets that humans can use to sound more romantic and flirty, including slowing down to create suspense, gently smiling when speaking, and keeping a sooth, consistent pace

The voice models generated by Sonantic can already express happiness and sadness, but flirty required a subtle approach, not possible with simple language.

As well as being flirty, the team have developed coy and teasing ‘styles’ of speech, to give non-playable characters in movies a much more realistic feel.

While the new video features a real actress, the voice over is completely artificially generated – with the AI voice reading a monologue about love.

It stars by leading you to believe the actress featured in the video is also reading the voiceover, but reveals ‘what you are hearing me say was never said by a human, it was generated by a computer. I am not real, I was never born.’

It was timed to come out on Valentines Day, showing how realistic AI can get at mimicking human speech patterns, something Sonantic calls the ‘CGI of Audio’. 

They’ve managed to achieve realistic ‘flirty audio’ thanks to non-verbal sounds, such as laughter, breathing, crying and scoffing.

The voice models generated by Sonantic can already express happiness and sadness, but flirty required a subtle approach, not possible with simple language

The voice models generated by Sonantic can already express happiness and sadness, but flirty required a subtle approach, not possible with simple language

Sonantic, based in London, England, produces expressive artificial intelligence voices for a range of uses, including Hollywood movies and computer games

Sonantic, based in London, England, produces expressive artificial intelligence voices for a range of uses, including Hollywood movies and computer games

QUALITIES OF AN ATTRACTIVE VOICE 

According to Dr Maggie Vaughan, a psychotherapist specializing in romantic relationships, there are five tips for an attractive voice:

  • Manage your tempo: slow down to create suspense; speed up to create excitement. 
  • Gently smile when speaking, which subconsciously helps you sound more likable. 
  • Take a deep breath and clear your throat so the words flow smoothly. 
  • Keep a smooth, consistent pace to create a strong sense of control and confidence. 
  • Speak in a slightly lower tone than usual; humans prefer soft spoken over loud. 

‘Human beings are incredibly complex by nature and our voices play a critical role in helping us connect with the world around us, said Sonantic CEO Zeena Qureshi.

‘At Sonantic, we are committed to capturing the nuances of the human voice, and we’re incredibly proud of these technological breakthroughs that we have brought to life through ‘What’s Her Secret?,” he explained in a statement. 

‘From flirting and giggling to breathing and pausing, this is the most realistic romantic demo we’ve created to date, helping us inch closer to our vision of being the CGI of Audio.’  

Dr. Maggie Vaughan, a New York City-based psychotherapist who specializes in romantic relationships, said there are key elements in speech patterns, tone and pacing that make or break a flirtatious conversation.

Upon reviewing ‘What’s Her Secret?’ she said they were all featured, including focus on tempo, breathing, smiling and tone changes.

The firm last hit the headlines in August 2021, when they announced they’d given Val Kilmer is voice back, by reacting the Tom Gun actors speech using recordings from before he developed throat cancer. 

Kilmer, whose career has spanned nearly four decades, has starred in blockbusters such as Top Gun, Willow, The Doors, Tombstone and Batman Forever. 

But after undergoing a tracheotomy in 2014 as part of his treatment for throat cancer, Kilmer’s voice is now barely recognisable. 

As well as being flirty, the team have developed coy and teasing 'styles' of speech, to give non-playable characters in movies a much more realistic feel

As well as being flirty, the team have developed coy and teasing ‘styles’ of speech, to give non-playable characters in movies a much more realistic feel

Luckily, Kilmer himself is also able to use the AI tool in his personal life, to help him communicate, rather than relying on a voice box to speak.  

Sonantic created a dashboard editor, that its customers – mainly in the world of film and gaming – can use to assign voices to characters.

It lets them change speech inflection, speed, volume and style – as well as dropping in non-verbal sounds to the script. 

Sonantic aren’t the only player in the synthetic voice market, with a virtual version of a young Luke Skywalker appearing on The Mandalorian developed by Respeecher.

Other firms are merging fully automatically generated people, including William Shatner and Albert Einstein, mixed with versions of their voice to match the age of the artificial recreation, also synthesized. 

The British start-up that’s given Val Kilmer his voice back: Artificial intelligence helps recreate Top Gun actor’s voice using recordings from before his throat cancer 

By Jonathan Chadwick

A British artificial intelligence (AI) company has recreated Hollywood actor Val Kilmer’s voice – with amazingly realistic results. 

London-based firm Sonantic used the actor’s voice recordings from throughout his career, which were fed to their AI to create the lifelike yet artificial mock-up.  

Film producers could potentially use the tool – described as ‘Photoshop for voice’ – for voiceovers if they have a role in mind that would be suited to Kilmer’s tones. 

Kilmer, whose career has spanned nearly four decades, has starred in blockbusters such as Top Gun, Willow, The Doors, Tombstone and Batman Forever. 

But after undergoing a tracheotomy in 2014 as part of his treatment for throat cancer, Kilmer’s voice is now barely recognisable. 

Luckily, Kilmer himself is also able to use the AI tool in his personal life, to help him communicate, rather than relying on a voice box to speak.

 

https://www.dailymail.co.uk/sciencetech/article-10512169/Scientists-develop-AI-flirt-using-non-word-sounds-sighs-breaths.html

Steve Liem

Learn More →