Kardome develops voice interaction technology that enhances speech recognition accuracy in noisy environments by utilizing deep learning and spatial hearing algorithms. This technology enables real-time, secure voice control for smart devices, addressing the challenges users face with traditional voice interfaces in complex soundscapes.
Funding
$13.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
HM+2Founders
Product
Problem
Voice-enabled devices often struggle to accurately recognize speech in noisy environments or when multiple people are speaking. Traditional voice user interfaces (VUIs) rely on cloud processing, which introduces latency and raises privacy concerns.
Solution
Kardome offers a deep-learning-based audio front-end technology that enhances speech recognition accuracy in challenging soundscapes. Their solution utilizes spatial hearing algorithms to isolate and enhance the target speaker's voice, even in the presence of background noise or multiple speakers. This technology enables real-time, secure voice control for smart devices, operating on the edge without relying on cloud processing. Kardome's technology can be integrated into various voice-enabled platforms and smart devices, improving the user experience and ensuring privacy.
Target Audience
Kardome's primary customers are automotive manufacturers, consumer electronics companies, healthcare providers, and kiosk manufacturers seeking to improve the accuracy and security of their voice-enabled devices.
Features
- Deep learning-based speech enhancement that outperforms standard voice processing algorithms
- Patented spatial hearing technology for isolating speech from multiple speakers in real-time
- Audio front-end technology that eliminates unwanted background noise
- Personalized wake word technology (MyWord) for custom voice experiences
- Voice ID technology for secure voice biometrics with high accuracy, even in noisy environments
- Multi-speaker isolation capabilities
- Edge-based processing for lower latency and enhanced privacy