System and method for addressing acoustic signal reverberation
AssigneeNuance Communications, Inc.
InventorsTobias Wolff, Lars Tebelmann
Life of this patent
Estimating the term…
Abstract
A system and method for addressing acoustic signal reverberation is provided. Embodiments may include receiving, at one or more microphones, a first audio signal and a reverberation audio signal. Embodiments may further include processing at least one of the first audio signal and the reverberation audio signal. Embodiments may also include limiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at signal least one of the first audio signal and the reverberation audio signal.
Claims18
A computer-implemented method comprising:
- receiving, at one or more microphones, a first audio signal;
- receiving, at the one or more microphones, a reverberation audio signal;
- processing at least one of the first audio signal and the reverberation audio signal;
- limiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal;
- and
- receiving a beamformer output at a postfilter, wherein the postfilter and beamformer are matched if a blocking matrix constraint is equivalent to a beamformer constraint.
A system for addressing acoustic signal reverberation comprising:
- one or more microphones having one or more processors configured to receive a first audio signal and a reverberation audio signal, the one or more processors further configured to process at least one of the first audio signal and the reverberation audio signal, the one or more processors further configured to limit a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal, the one or more processors further configured to receive a beamformer output at a postfilter, wherein the postfilter and beamformer are matched if a blocking matrix constraint is equivalent to a beamformer constraint.
A computer-implemented method for addressing acoustic signal reverberation comprising:
- receiving, at one or more microphones, a first audio signal from a first audio signal source;
- receiving, at the one or more microphones, a reverberation audio signal from a reverberation audio signal source;
- processing at least one of the first audio signal and the reverberation audio signal at a beamformer;
- limiting a model based reverberation equalizer using a temporal constraint for direct sound distortions, the model based reverberation equalizer configured to generate one or more outputs, based upon, at least in part, at least one of the first audio signal and the reverberation audio signal;
- receiving the one or more outputs from the model based reverberation equalizer at a postfilter;
- and
- receiving a beamformer output at the postfilter, wherein the postfilter and beamformer are matched if a blocking matrix constraint is equivalent to a beamformer constraint.
Dependencies are inferred from the claim text.