Talker change detection

This invention describes a method to detect if a new person is speaking or if the current speaker has moved dramatically. It works by using two microphones to capture sound and then analyzing the unique 'phase pattern' of the sound waves between them, specifically using the phase of their cross power spectral density. By comparing this current phase pattern to a previously established one, the system can identify a change in the sound source's location or identity, which can then be used to control other audio processing.

Why it matters: Filed before widespread adoption of multi-microphone arrays in consumer devices and significant advancements in real-time audio processing, which could enhance its performance and applicability.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, DSP expertise

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10