US Patent Application 18349920. SEPARATION OF SELF-VOICE SIGNAL FROM A BACKGROUND SIGNAL USING A SPEECH GENERATIVE NETWORK ON A WEARABLE DEVICE simplified abstract
SEPARATION OF SELF-VOICE SIGNAL FROM A BACKGROUND SIGNAL USING A SPEECH GENERATIVE NETWORK ON A WEARABLE DEVICE
Organization Name
Inventor(s)
Lae-Hoon Kim of San Diego CA (US)
Dongmei Wang of Bellevue WA (US)
Fatemeh Saki of San Diego CA (US)
Taher Shahbazi Mirzahasanloo of San Diego CA (US)
Erik Visser of San Diego CA (US)
Rogerio Guedes Alves of Macomb Township MI (US)
SEPARATION OF SELF-VOICE SIGNAL FROM A BACKGROUND SIGNAL USING A SPEECH GENERATIVE NETWORK ON A WEARABLE DEVICE - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18349920 Titled 'SEPARATION OF SELF-VOICE SIGNAL FROM A BACKGROUND SIGNAL USING A SPEECH GENERATIVE NETWORK ON A WEARABLE DEVICE'
Simplified Explanation
The abstract describes a wearable device that can detect and separate a person's voice from background noise using multiple microphones. It can also filter and amplify external audio signals during a listen-through operation. The device then produces an output audio signal that includes both the person's voice and the external audio.
Original Abstract Submitted
A wearable device may include a processor configured to detect a self-voice signal, based on one or more transducers. The processor may be configured to separate the self-voice signal from a background signal in an external audio signal based on using a multi-microphone speech generative network. The processor may also be configured to apply a first filter to an external audio signal, detected by at least one external microphone on the wearable device, during a listen through operation based on an activation of the audio zoom feature to generate a first listen-through signal that includes the external audio signal. The processor may be configured to produce an output audio signal that is based on at least the first listen-through signal that includes the external signal, and is based on the detected self-voice signal.
