Innovative sign language recognition and translation technology

SignLanguage employs machine translation and natural language processing to be the first company in the world with technology that can fully recognize and translate sign language to English.
A woman's hands positioned with the palms facing up

Challenges with signed languages

To create such advanced and complex technology, in-depth knowledge and expertise of a range of fields is required.

Human languages are astoundingly complex and diverse. We express ourselves in infinite ways, such as through speaking or signing. Unlike spoken languages, signed languages are perceived visually. The expressive and visual nature of sign languages allows its users to process elements simultaneously. At the same time, it also creates a unique set of challenges for sign language technology.

SignAll’s success can be attributed to many factors, including high levels of knowledge in the following areas:

Deaf culture and community
Technology (computer vision + artificial intelligence)
Linguistic expertise
Smiling and signing woman

Major components of sign language

Each sign is made up of key elements, or parameters, performed by the signer to convey its meaning. SignAll has developed a method for detecting these important features in order to fully recognize sign language.

Body

The space and location used by the signer are part of the non-manual markers of sign language.

Hands

The shape, orientation, movement, and location of the hands are some of the key parameters of sign language.

Face

Other non-manual markers include the eyes, mouth, brows, or head movements such as nodding or shaking.

A white young woman signing and smiling. Skeleton tracking lines are on top of her hands, fingers, upper body and face

Capturing and digitizing the elements of sign language

SignAll's core technology uses visual input from the external world and converts this information into data which can be processed by the computer.

  • Visual input can be collected through one or multiple cameras.
  • Cameras can be 2D or 3D, or any combination of these (e.g., a single 2D camera, one 2D camera + two 3D cameras, three 3D cameras, etc.)
  • The sophistication of the use case delivered is directly related to the quality of visual input.

One piece of the puzzle

Capturing these components is the first step towards effective sign language translation, but a much more complex process is required to turn this data into meaningful information.

Not just another sign-language glove

Over the years, there have been many attempts to use technology to translate sign language, yet unfortunately these all have failed to consider all of the important factors that make up sign language.

Understanding the complexities

The combined expertise of developers, researchers, linguists, and sign language experts has allowed SignAll to employ technology to capture and analyze the key elements of sign language.

Converting data into meaningful information

Converting any human language into something understandable to computers is itself a heavy task, but the spatial and visual nature of sign languages add an entirely bigger challenge to the task.

Capture the visual data

Depth cameras create point cloud images, and an additional camera is used for color detection. The images are then merged together to map the visual and spatial elements of the signer.

Process the data

Images represent signs which may have multiple meanings, similar forms, or have different parts of speech (e.g. a noun vs. a verb). The visually recognized data is referenced against our database to retrieve all the possible sign IDs.

Narrow the selection

In some cases, there could be over 100 combinations of the sign IDs, as they can also represent different syntactic roles within the sentences. Using a variety of machine translation approaches, the probability of different combinations is calculated, and the top 3 most likely options are identified.

Select desired translation

The top 3 results are displayed on the screen for the user. The user then selects the translation which best matches their sign language.

Present the option

The selected sentence is displayed on the screen for the hearing user to read. It can also be voiced using text-to-speech technology.