Keyword Spotting

Rapidly Develop Custom Wake Word and Command Vocabularies

Always-On Custom Wake Word Detection

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.

Rapid Production Quality Models
SensiML's efficient workflow provides numerous aids to automate the modeling process
  • 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
SensiML VoiceID Technology

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

Platforms and Plans
SensiML offers complete Knowledge Pack development services allowing you to focus on your application. Our team can devise a customized project plan using your application audio training data to create a tailored voice recognition library ready to drop into your application.
Platforms and Plans
For project teams with basic machine learning familiarity, desire to learn, or needing to undertake the tasks entirely in-house, SensiML offers its ML Analytics Toolkit suite. A true end-to-end workflow, SensiML Analytics Toolkit supports the complete process from data collection and labeling to Knowledge Pack generation and testing.