Open up the possibilities of smart voice command by integrating custom wake word and command phrases directly into your microphone-equipped embedded product. No dependency required from third party smarthome hubs, your voice control feature is fully self-contained and customizable to your own product's user experience goals.
SensiML's graphical UI pipeline makes it easy and fast to tailor your command vocabulary into optimized deep-learning ML embedded code available in library or C source form for rapid integration. No data science expertise required.
- Automated dataset labeling assistance
- Dataset augmentation (ex. noise, pitch, cadence variations)
- Pre-trained keyword spotting templates
- Automated model test/validation
- Point-and-click model porting to 25+ embedded platforms
Go beyond command and wakeword recognition with SensiML's Voice ID technology. Imagine the possibilities for improved user experience, security, and contextual insight that come from knowing which user is speaking to your device.
With personalized model adaptation and a simple user pre-training, your IoT device can add speaker identification to complement voice wake word and phrase detection
