The current products on the market for the Deaf and hard of hearing are extremely limited. Assistive hearing devices—such as cochlear implants—help indicate or amplify sound, but do not assign meaning to what’s heard. Other visual cues—such as flashing lights—help to notify of a doorbell, incoming phone call, or fire alarm, but are only single use.

There is no product available that can differentiate sounds. This leaves consumers with a handful of single-sound devices, but nothing that can distinguish a microwave from a baby crying, from glass breaking, and so on.

The barrier of inventing a product like this has been the lack of data. It would take literally millions of sound samples to create a machine-learning model that could report with any level of confidence. And that's exactly the problem we solved with See Sound, sourcing sound data from 2 million YouTube audio clips.

The Deaf and hard of hearing have had to buy multiple different products to monitor household sounds, but nothing that’s had the ability to distinguish between a microwave, baby crying, or any other household sound. In a time when sound recognition technology is constantly advancing, the availability and accessibility of smart devices for the Deaf is severely lacking.

See Sound is a revolutionary home device powered by an AI-learning model that is able to not only listen for a multitude of sounds but distinguish between them with a high level of accuracy. Once a sound is identified, See Sound alerts users via their various devices, including smart phones, watches, and smart lights.

See Sound is a significant advancement for this underserved community. No longer do the Deaf need to solely rely on their partners or pets to alert them to noises around their home. They can finally see sound.

See Sound is an iOT product that runs on a state-of-the-art sound classification neural net. We designed the device with a built-in plug and a neutral color palette to seamlessly integrate into homes. Its concave design subtly hints to the shape of an ear, but is functional, helping to funnel sound to the omnidirectional microphone at the core of the device. Additionally, we needed to create a clear visual experience for our Deaf users. To address, we ensured that each sound was translated into a simple visual readout on a user’s smart device.

For the software, the device’s sound library leverages a data set of over 2 million human-labeled 10-second sound clips from YouTube’s billions of user videos. Each were manually analyzed, annotated, and organized into the sound categories. Our machine-learning model was then trained with this data to achieve an industry-leading accuracy level (mean average precision of 0.360).

With 2 patents secured and years of development in place, See Sound finally launched its e-commerce sites in the US in 2020. Our consumer pricing model at launch was in place to drive high adoption, market share, and demand, in order to maximize acceptance into Americans with Disabilities Act’s (ADA’s) government contracts.

After launching our website and social accounts, we saw a 400% increase in website traffic with over 1000+ sign ups and 448K users reached on Facebook. Emails to tease preorders were sent to 2,000 recipients, garnering high engagement rates (36% open rate; 12% click through). Additionally, a separate marketing effort targeted an exclusive group of 160 priority consumers, which saw even higher engagement (67% open rate; 33% click through).

We sold over 1000 units in the preorder launch phase but are currently looking for a new manufacturing partner after our manufacturing partner fell through during the pandemic.