Applied Consensus: Which Station Should Respond?
summary
Describes a backend streaming algorithm that selects exactly one smart device (a "Station") to respond when multiple devices detect a voice assistant wake word. The talk explains how the algorithm finds the single best device, scales easily across many devices, and has minimal impact on response latency.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 5:45Consensus algorithm theory
- 7:10Memcache version
- 11:45VDB and microservices
- 19:33Device capability handling
- 25:52Development lessons
- 26:56Q&A
related talks
36mVoice Enabling Mobile Apps and Custom Hardware Devices
23mContact Center Voice AI: Low-Latency Intelligence Extraction from Messy Audio Streams
16mAgentic Ambient Active Listening
27mPlay
48mDistributed Consensus Algorithms
29mEngineering Machine Learning Technologies
35mHaving a Voice on Android: How hard can it be?
39mIt's All in the Data: The ML Behind Alexa's AI Systems