Use when building voice interfaces for robots — wake word detection, streaming ASR, on-device TTS, barge-in, mic arrays near motors, or voice command pipelines. Provides expert knowledge on edge speech stacks (Porcupine/openWakeWord, faster-whisper, Piper), acoustic noise mitigation on mobile platfo
Use when building voice interfaces for robots — wake word detection, streaming ASR, on-device TTS, barge-in, mic arrays near motors, or voice command pipelines. Provides expert knowledge on edge speech stacks (Porcupine/openWakeWord, faster-whisper, Piper), acoustic noise mitigation on mobile platforms, and safety-critical intent design where voice must never directly trigger motion.