P053Filed

Acoustic Field Synthesis via Ternary DSP

Speech recognition at milliwatt power — always listening, ternary-efficient.

AU Application
2023900053
Filing Date
5 October 2023
Index Number
P053
Figures
11 figures
Batch / Category
Media & Codec

Explore the Vision

Discover this technology through five complementary perspectives — from technical architecture to partnership outcomes. Each layer reveals a different aspect of how this innovation creates value.

Speech recognition at milliwatt power — always listening, ternary-efficient.

What It IS

Technical Vision

The architectural essence — what makes this technology work

A microphone listening continuously — consuming less power than an LED — its ternary voice activity detector classifying every moment as speech, silence, or non-speech in three states at 50 microwatts. When speech arrives, the full processing pipeline wakes. Watchful efficiency.

1/5
Explore the buyer's journey across 5 perspectives

Abstract

Generation of spatial audio and acoustic field reconstruction using multiply-free ternary operations, enabling immersive audio on edge devices.

Visual Essence

A microphone listening continuously — consuming less power than an LED — its ternary voice activity detector classifying every moment as speech, silence, or non-speech in three states at 50 microwatts. When speech arrives, the full processing pipeline wakes. Watchful efficiency.

Visual Family:wave-crystal

Technology Domains

Related Patents

From the wave-crystal visual family