GOOGLE LLC (20240249741). Guided Speech Enhancement Network simplified abstract
Contents
Guided Speech Enhancement Network
Organization Name
Inventor(s)
George Chiachi Sung of San Diego CA (US)
Yang Yang of San Diego CA (US)
Shao-Fu Shih of Mountain View CA (US)
Hakan Erdogan of Lexington MA (US)
Jamie Menjay Lin of San Diego CA (US)
Guided Speech Enhancement Network - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240249741 titled 'Guided Speech Enhancement Network
The method described in the abstract involves processing audio data using a trained guided speech-enhancement network to enhance the audio signal captured by an audio input device and spatially-filtered by a beamformer.
- The method receives reference audio data and spatially-filtered audio data from a beamformer.
- The beamformer attenuates interfering signals in the spatially-filtered audio data based on additional audio data captured by other audio input devices.
- A trained guided speech-enhancement network processes the reference audio data and spatially-filtered audio data to further attenuate interfering signals in the enhanced audio data.
- The output of the method is enhanced audio data with reduced interference, improving the overall audio quality.
Potential Applications: - Speech enhancement in noisy environments - Audio conferencing systems - Hearing aid technology
Problems Solved: - Reduction of interfering signals in audio data - Improved speech intelligibility in challenging acoustic environments
Benefits: - Enhanced audio quality - Improved communication in noisy settings - Better user experience in audio applications
Commercial Applications: Title: Advanced Speech Enhancement Technology for Audio Devices This technology can be applied in audio devices such as smartphones, tablets, and conference systems to improve speech clarity and overall audio quality, leading to better user satisfaction and market competitiveness.
Questions about the technology: 1. How does the trained guided speech-enhancement network improve the audio quality in the method described? 2. What are the potential real-world applications of this technology in different industries?
Original Abstract Submitted
a method includes receiving, as input, reference audio data representing a reference audio signal captured by an audio input device. the method also includes receiving, as input, from a beamformer, spatially-filtered audio data representing an output of the beamformer, the beamformer configured to spatially filter, based on additional audio data captured by one or more additional audio input devices, the reference audio data to attenuate one or more interfering signals in the spatially-filtered audio data. the method processes, using a trained guided speech-enhancement network, the reference audio data and the spatially-filtered audio data to generate, as output, enhanced audio data, the guided speech-enhancement network processing the reference audio data and the spatially-filtered audio data to further attenuate, in the enhanced audio data, the one or more interfering signals attenuated by the beamformer.
