Voice Enabling Mobile Apps and Custom Hardware Devices
summary
Keen Research ships an on-device speech SDK (iOS, Android, Linux, Unity) used by Noggin, PBS Kids and Novel Effect to run local ASR models tuned for kids and by Hey Metronome and Mira Check for hands-free control (example: “set tempo to 100 BPM” works reliably). The talk contrasts cloud vs on-device tradeoffs, details wake‑word cascades, microphone arrays and beamforming, and stresses acoustic echo cancellation for apps that play audio while listening; evaluation uses word‑error‑rate on an authentic test set.
AI-written summary · about
chapters (6)
- 0:00Introduction and overview
- 3:17Real-world voice use cases
- 11:08How voice assistants work
- 22:00Key voice technology components
- 30:07Choosing the right voice solution
- 34:41Tips for voice-enabled apps
related talks
22mOn-Device Speech Recognition for Mobile Devices and Custom Hardware
47mBuilding Voice-First Android Apps- 47mBuilding Voice-First Android Apps
06mSensing to Hear: Speech Enhancement for Mobile Devices Using Acoustic Signals
35mHaving a Voice on Android: How hard can it be?
11mVOICE Summit 2019 | VED Talks | Melissa Hammersley | July 23
43mThe State of Voice Interactions on Android
42mThe State of Voice Interactions on Android