17382166. NOISE SUPPRESSION USING TANDEM NETWORKS simplified abstract (QUALCOMM Incorporated)
Contents
NOISE SUPPRESSION USING TANDEM NETWORKS
Organization Name
Inventor(s)
Vahid Montazeri of San Diego CA (US)
Van Nguyen of San Diego CA (US)
Hannes Pessentheiner of Graz (AT)
Lae-Hoon Kim of San Diego CA (US)
Erik Visser of San Diego CA (US)
Rogerio Guedes Alves of Macomb Township MI (US)
NOISE SUPPRESSION USING TANDEM NETWORKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17382166 titled 'NOISE SUPPRESSION USING TANDEM NETWORKS
Simplified Explanation
The patent application describes a device with memory and processors that receive audio data from two microphones. The processors provide the audio data to two noise-suppression networks, which generate noise-suppressed audio frames. These frames are then provided to an attention-pooling network, which generates an output noise-suppressed audio frame.
- The device has memory and processors to execute instructions.
- It receives audio data from two microphones.
- The audio data is provided to two noise-suppression networks.
- The networks generate noise-suppressed audio frames.
- The frames are then provided to an attention-pooling network.
- The attention-pooling network generates an output noise-suppressed audio frame.
Potential Applications
- Speech recognition systems
- Voice assistants
- Teleconferencing systems
- Hearing aids
- Audio recording devices
Problems Solved
- Reducing background noise in audio recordings
- Improving speech recognition accuracy in noisy environments
- Enhancing the quality of audio captured by microphones
Benefits
- Improved audio quality
- Enhanced speech recognition performance
- Better user experience in noisy environments
- Increased accuracy in audio recordings
Original Abstract Submitted
A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to receive audio data including a first audio frame corresponding to a first output of a first microphone and a second audio frame corresponding to a second output of a second microphone. The one or more processors are also configured to execute the instructions to provide the audio data to a first noise-suppression network and a second noise-suppression network. The first noise-suppression network is configured to generate a first noise-suppressed audio frame and the second noise-suppression network is configured to generate a second noise-suppressed audio frame. The one or more processors are further configured to execute the instructions to provide the noise-suppressed audio frames to an attention-pooling network. The attention-pooling network is configured to generate an output noise-suppressed audio frame.