Skip to main content

A revolution in speech animation?

I have always been fascinated by animated characters.  We know there is more to speech than simply words.  Facial expression adds significantly to our understanding.  As a deaf person I also know too well how precise movement of the lips and face help in my understanding of the spoken word. 

Forming speech is complex. About a hundred different muscles in the chest, neck, jaw, tongue, and lips must work together in forming speech. Every word or short phrase that is physically spoken is followed by its own unique arrangement of muscle movements.   No wonder then that animations can often appear flat and characterless. 

New research from the University of East Anglia (UK) could revolutionise the way that animated characters deliver their lines.

Animating the speech of characters such as Elsa and Mowgli has been both time-consuming and costly. But now computer programmers have identified a way of creating natural-looking animated speech that can be generated in real-time as voice actors deliver their lines.

The discovery was unveiled in Los Angeles at the world’s largest computer graphics conference - Siggraph 2017. This work is a collaboration which includes UEA, Caltech and Carnegie Mellon University

Researchers show how a ‘deep learning’ approach – using artificial neural networks – can generate natural-looking real-time animated speech.

As well as automatically generating lip sync for English speaking actors, the new software also animates singing and can be adapted for foreign languages. The online video games industry could also benefit from the research – with characters delivering their lines on-the-fly with much more realism than is currently possible – and it could also be it can be used to animate avatars in virtual reality.

A central focus for the work has been to develop software which can be seamlessly integrated into existing production pipelines, and which is easy to edit.

Lead researcher Dr Sarah Taylor, from UEA’s School of Computing Sciences, said: “Realistic speech animation is essential for effective character animation. Done badly, it can be distracting and lead to a box office flop.

“Doing it well however is both time consuming and costly as it has to be manually produced by a skilled animator. Our goal is to automatically generate production-quality animated speech for any style of character, given only audio speech as an input.”

The team’s approach involves ‘training’ a computer to take spoken words from a voice actor, predict the mouth shape needed, and animate a character to lip sync the speech.

This is done by first recording audio and video of a reference speaker reciting a collection of more than 2500 phonetically diverse sentences. Their face is tracked to create a ‘reference face’ animation model.

The audio is then transcribed into speech sounds using off-the-shelf speech recognition software.

This collected information can then be used to generate a model that is able to animate the reference face from a frame-by-frame sequence of phonemes. This animation can then be transferred to a CG character in real-time.

‘Training’ the model takes just a couple of hours. Dr Taylor said: “What we are doing is translating audio speech into a phonetic representation, and then into realistic animated speech.”

The method has so far been tested against sentences from a range of different speakers. The research team also undertook a subjective evaluation in which viewers rated how natural the animated speech looked.

Dr Taylor said: “Our approach only requires off-the-shelf speech recognition software, which automatically converts any spoken audio into the corresponding phonetic description. Our automatic speech animation therefore works for any input speaker, for any style of speech and can even work in other languages.

“Our results so far show that our approach achieves state-of-the-art performance in visual speech animation. The real beauty is that it is very straightforward to use, and easy to edit and stylise the animation using standard production editing software.”

Comments

Popular posts from this blog

Palm Oil production killing the planet

Bad trade and bad products are killing our planet. We have said this before on The Thin End. There is no better example than that of palm oil. It is used ubiquitously in so many products, and its production is a major factor destroying rainforests and threatening precious species.

Demand for palm oil is 'skyrocketing worldwide'. It is used in packaging and in so much of our snack foods, cookies, crackers, chocolate products, instant noodles, cereals, and doughnuts, and the list goes on.
Bad for the planet So, why is this so bad for the planet?

The oil is extracted from the fruit of the oil palms native to Africa. It is now grown primarily in Indonesia and Malaysia, but is also expanding across Central and West Africa and Latin America.

Palm oil production is now one of the world's leading causes of rainforest destruction, and this is impacting adversely some of the world's most culturally and biologically diverse ecosystems. Irreplaceable wildlife species like t…

Nicotine exposure in pregnancy linked to cot death

Nicotine exposure during pregnancy, whether from smoking cigarettes, or nicotine patches and e-cigarettes, increases risk of sudden infant death syndrome – sometimes known as “cot death” – according to new research published in The Journal of Physiology.

Sudden infant death syndrome (SIDS) is the sudden and unexpected death of an infant under 12 months of age occuring typically while sleeping. Failure of auto resuscitation, the ability to recover normal heart rate and breathing following gasping caused by lack of oxygen in the brain, has been recorded in human SIDS cases.



Smoking increases risk for SIDS Over the last decade, use of cigarettes has declined significantly, however, over 10% of pregnant women still smoke during pregnancy. Over recent years nicotine replacement therapies, such as nicotine patches or e-cigarettes, have been prescribed to women who wish to quit smoking during their pregnancy. However, nicotine replacement therapies may not protect infants from SIDS. 
With inc…

Maternal depression can impact child mental and physical health

Maternal depression has been repeatedly linked with negative childhood outcomes, including increased psychopathology.  Now, a new study shows that depression in mothers may impact on their children's stress levels,  as well as their physical and mental well-being throughout life.

In the study, published in the journal  Depression & Anxiety,  the researchers followed 125 children from birth to 10 years.

At 10 years old, the mothers’ and children’s cortisol (CT) and secretory immunoglobulin (s-IgA)—markers of stress and the immune system (see below)—were measured, and mother-child interaction were observed.
Psychiatric assessment  The mothers and children also had psychiatric diagnoses, and the children's externalising and internalising symptoms were reported.



Internalising disorders include depression, withdrawal, anxiety, and loneliness. They are often how we 'feel inside', such as  anger, pain, fear or hurt, but may not show it.  In contrast, externalising symptom…