Neural-network-based approach for speech denoising
AssigneesThe Trustees of Columbia University in the City of New York, SoftBank Corp.
InventorsChangxi Zheng, Ruilin Xu, Rundi Wu, Carl Vondrick, Yuko Ishiwaka
Life of this patent
Estimating the term…
Abstract
Disclosed are methods, systems, device, and other implementations, including a method that includes receiving an audio signal representation, detecting in the received audio signal representation, using a first learning model, one or more silent intervals with reduced foreground sound levels, determining based on the detected one or more silent intervals an estimated full noise profile corresponding to the audio signal representation, and generating with a second learning model, based on the received audio signal representation and on the determined estimated full noise profile, a resultant audio signal representation with a reduced noise level.
Claims8
A method comprising:
- receiving an audio signal representation;
- detecting in the received audio signal representation, using a first learning model, one or more silent intervals with reduced foreground sound levels;
- determining based on the detected one or more silent intervals an estimated full noise profile corresponding to the audio signal representation;
- and
- generating with a second learning model, based on the received audio signal representation and on the determined estimated full noise profile, a resultant audio signal representation with a reduced noise level.
The method of claim I, wherein detecting using the first learning model the one or more silent intervals comprises:
- segmenting the audio signal representation into multiple segments, each segment being shorter than an interval length of the received audio signal representation;
- transforming the multiple segments into a time-frequency representation;
- and
- processing the time-frequency representation of the multiple segments using a first learning machine, implementing the first learning model, to produce a noise vector that includes, for each of the multiple segments, a confidence value representative of a likelihood that the respective one of the multiple segments is a silent interval.
A system comprising:
- a receiver unit to receive an audio signal representation;
- and
- a controller, implementing one or more learning engines, in communication with the receiver unit and a memory device to store programmable instructions, to:
- detect in the received audio signal representation, using a first learning model, one or more silent intervals with reduced foreground sound levels;
- determine based on the detected one or more silent intervals an estimated full noise profile corresponding to the audio signal representation;
- and
- generate with a second learning model, based on the received audio signal representation and on the determined estimated full noise profile, a resultant audio signal representation with a reduced noise level.
A non-transitory computer readable media storing a set of instructions, executable on at least one programmable device, to:
- receive an audio signal representation;
- detect in the received audio signal representation, using a first learning model, one or more silent intervals with reduced foreground sound levels;
- determine based on the detected one or more silent intervals an estimated full noise profile corresponding to the audio signal representation;
- and
- generate with a second learning model, based on the received audio signal representation and on the determined estimated full noise profile, a resultant audio signal representation with a reduced noise level.
Dependencies are inferred from the claim text.