Kardome’s Year in Review: Taking Voice Technology to Where It’s Never Been Before
Kardome is excited to share our accomplishments of the past year. We’ve made huge strides with our voice user interface (VUI) technology, and we want to take this opportunity to reflect on what it means to be at the forefront of voice tech. For us, it all comes down to one thing: our mission.
Kardome's mission is to advance speech recognition technology that will transform how people communicate, connect, and interact with machines—and each other.
To do that successfully, we need partnerships with amazing people and organizations who are as passionate about innovation as we are. And that’s what we have been working on the past year—building relationships with key people from leading organizations who share our philosophy.
We’ve also expanded our VUI technology to include Voice ID, 3D audio analysis, and domain-specific ASR. These new technologies will provide superior speech and voice recognition for the consumer electronics, automotive, and enterprise sectors.
Following is more on our new Spatial Listening Software Suite, some of our notable accomplishments in the past year, and new partnerships we’ve formed that will help us achieve our mission—voice first for all.
Introducing Kardome’s Spatial Listening Software
This year we introduced our Spatial Listening Software Suite. Spatial listening enables consumer electronics, automotive, and enterprise hardware developers to create next-generation speech recognition devices that:
- Understand who is talking (voice identification)
- Where they are located (3D audio analysis)
- What they are saying (domain-specific Automatic Speech Recognition [ASR] )
This superior speech recognition capability occurs even in the most challenging voice environments. At the same time, user privacy, immediacy, and independence is maintained with spatial listening implemented using edge-based technology.
The following is a sample of our new Spatial Listening Software Suite in action:
Forging New Partnerships to Advance Kardome’s VUI
We’ve entered several new partnerships with major technology companies that have paved the way to expand Kardome’s voice technology in the years to come.
From Renault Group and Hyundai in the automotive industry and major tech giants such as Intel and Yandex to longstanding audio solution companies like Knowles, Kardome is forging a path to create superior voice recognition for smart devices.
Kardome also presented its voice technology at Viva Tech, one of Europe's biggest startup and tech events, the 19th annual Shanghai International Industrial Automation and Robot Exhibition, and the Self-Service Innovation Summit in Florida.
Notable Mentions and Awards
Exciting achievements for Kardome include placing first in the Reinhold Cohn Group Startup Competition out of a group of over 160 startups.
The Reinhold Cohn Group holds the annual Startup Competition to discover scalable technological solutions that address various challenges by connecting global organizations and innovative startups.
Kardome placed first in the competition for its AI-driven source separation and noise-reduction technology that gives accurate, real-time voice command input and audio output in any environment.
Kardome also won the Huawei Moving Audio Tech Forward Challenge. The challenge asked participants to offer innovative hardware or software technology solutions to capture and transmit audio, protect and reproduce audio, and render and adapt audio content to a user and the environment.
Kardome met this challenge with its technology that improves audio quality and speech intelligibility for VUI devices, such as voice assistants, speech recognition devices, and speech-to-text applications.
Additionally, the Startup Pill listed Kardome as one of the 30 Quality Real-Time Startups To Look Out For In 2021.
A Word From Our CEO/Co-founder Dani Cherkassky
We at Kardome believe that voice is the most natural and efficient way for humans to interact with machines—how humans interact between themselves.
The challenge is human-machine interaction is still primarily hand-operated (pushing buttons), even though voice interfaces have existed for decades. So why is voice technology still falling behind compared to touch controls and interfaces?
There are two main reasons: existing state-of-the-art VUIs do not work well in noisy environments and are cumbersome.
Today, there are two significant types of VUIs:
First, there are the well-known voice assistants—provided by Amazon, Google, Apple, and other cloud service providers.
These voice-based devices are great for search, navigation, and streaming.
However, employing voice assistance for a functional interface—i.e., opening a window or adjusting the TV volume—results in a very cumbersome two-step request. E.g., “Hey Alexa, turn down the volume of my Hisense TV in my living room.”
This cumbersome interface results in almost zero customer engagement.
The second widely used VUIs are ones that smart devices manufacturers, be it for cars or TVs, build and integrate with their edge systems.
They typically build these interfaces from off-the-shelf components, which only partially fit together. The result is that these VUIs can service customers only when the environment is relatively quiet.
Fulfilling the Voice First Mission
We at Kardome decided our mission is to equip machines with a human-level speech understanding to address existing VUI challenges. So we put together an incredibly talented team of speech AI experts that developed our proprietary spatial listening technology to meet that goal.
Our edge-based, spatial listening technology will tackle the most challenging VUI problems by enabling machines to understand who is talking, where they are, and what they are talking about—in any environment. Kardome’s Spatial Listening Suite will give users privacy, immediacy, and independence.
What does the future hold for Kardome?
For Kardome, our goal is to be at the forefront of voice technology. What does that mean? It means doing something that no one else is—creating voice user interface technology like nothing else out there.
We want to make it easy for people to use their voices to control their devices, get information, and interact with family and colleagues over video/audio platforms.
With our new Spatial Listening Software Suite, new partnerships, and more exciting developments to come, we'll be taking Voice Technology to new heights in the New Year and beyond.