Patents by Inventor Athanasios Gotsopoulos
Athanasios Gotsopoulos has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240385798Abstract: A robotic system is provided, which automatically changes settings on an audio system. The audio system (e.g., an instrument amplifier, effect processor, etc.) typically includes one or more controls that impact the operation of the audio system. Correspondingly, the robotic system includes a device interface coupled to a control sequencer. The device interface adapts to one or more controls of the audio system that are to be changed. In this regard, the device interface includes one or more control couplers. Each control coupler is adapted to a corresponding control of the audio system to be changed. The control sequencer provides a control sequence to the device interface that causes the control coupler(s) to vary the settings on the audio system. In practical applications, a combination of sequence values of the control sequence can represent a sufficiently high number of samples to determine a responsive behavior of the audio system.Type: ApplicationFiled: May 16, 2024Publication date: November 21, 2024Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Tuomas Juvela, Aleksi Tapani Peussa, Kimmo Erik Antero Rauhanen, Thomas Sherson
-
Patent number: 12014108Abstract: A robotic system is provided, which automatically changes settings on an audio system. The audio system (e.g., an instrument amplifier, effect processor, etc.) typically includes one or more controls that impact the operation of the audio system. Correspondingly, the robotic system includes a device interface coupled to a control sequencer. The device interface adapts to one or more controls of the audio system that are to be changed. In this regard, the device interface includes one or more control couplers. Each control coupler is adapted to a corresponding control of the audio system to be changed. The control sequencer provides a control sequence to the device interface that causes the control coupler(s) to vary the settings on the audio system. In practical applications, a combination of sequence values of the control sequence can represent a sufficiently high number of samples to determine a responsive behavior of the audio system.Type: GrantFiled: February 11, 2022Date of Patent: June 18, 2024Assignee: Neural DSP Technologies OyInventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Tuomas Juvela, Aleksi Tapani Peussa, Kimmo Erik Antero Rauhanen, Thomas William Sherson
-
Publication number: 20240161720Abstract: A neural network emulates a behavior of a reference audio system for at least two control settings. A process, for each control setting, receives control position data designating a select control setting of the reference audio system as conditioning for the neural network, communicates an input to the reference audio system and captures a target output, maps parameters of the neural network such that, responsive to the input, a neural output resembles the target output, scores by a loss function, a similarity of the neural network output compared to the target output of the reference audio system, and utilizes the similarity derived from the loss function to modify model parameters of the neural network. A graphical user interface enables a user to select a virtual control setting within the graphical user interface such that the neural network models the reference audio system at the corresponding control setting.Type: ApplicationFiled: November 15, 2023Publication date: May 16, 2024Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Tuomas Jevela, Aleksi Tapani Peussa, Kimmo Erik Antero Rauhanen, Thomas William Sherson, Jaakko Makinen, Stylianos I. Mimilakis
-
Publication number: 20230119557Abstract: A process is provided for training a neural network that digitally models an audio system. A sound source is utilized to electrically couple a test signal into an input of a reference audio system. The output of the reference audio system is collected into an audio interface coupled to a computer. A neural network is then trained using the test signal and the captured information to derive a set of weight vectors with appropriate values such that the overall output of the neural network converges towards an output representative of the reference audio system, and a signal in the time domain from a musical instrument is processed through the trained neural network with a latency under 20 milliseconds. A graphical user interface then outputs a graphical representation of the trained neural network, where the graphical representation visually displays at least one virtual control for interaction by a user.Type: ApplicationFiled: December 16, 2022Publication date: April 20, 2023Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Juvela, Thomas William Sherson
-
Patent number: 11532318Abstract: A neural network is trained to digitally model a reference audio system. Training is carried out by repeatedly performing a set of operations. The set of operations includes predicting by the neural network, a model output based upon an input, where the output approximates an expected output of the reference audio system, and the prediction is carried out in the time domain. The set of operations also includes applying a perceptual loss function to the neural network based upon a determined psychoacoustic property, wherein the perceptual loss function is applied in the frequency domain. Moreover, the set of operations includes adjusting the neural network responsive to the output of the perceptual loss function. A neural model file is output that can be loaded to generate a virtualization of the reference audio system.Type: GrantFiled: January 9, 2020Date of Patent: December 20, 2022Assignee: Neural DSP Technologies OyInventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Juvela, Thomas William Sherson
-
Publication number: 20220262330Abstract: A system for emulating a physical audio system comprises a user interface (UI) and a digital model of the physical audio system. The UI comprises virtual controls for changing virtual control settings (e.g., a virtual volume control for changing a virtual volume setting, etc.). A change in a virtual control setting produces a change to the output of the digital model. Because the digital model emulates the behavior of the physical audio system, changes to the model output in response to changes in the virtual control settings correspond to changes in the audio output in response to changes in the physical control settings. For example, if the physical audio system is an audio amplifier with control knobs, then the virtual controls will affect the output of the digital model like the control knobs affect the audio output of the audio amplifier.Type: ApplicationFiled: February 11, 2022Publication date: August 18, 2022Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Tuomas Juvela, Aleksi Tapani Peussa, Kimmo Erik Antero Rauhanen, Thomas William Sherson
-
Publication number: 20220261209Abstract: A robotic system is provided, which automatically changes settings on an audio system. The audio system (e.g., an instrument amplifier, effect processor, etc.) typically includes one or more controls that impact the operation of the audio system. Correspondingly, the robotic system includes a device interface coupled to a control sequencer. The device interface adapts to one or more controls of the audio system that are to be changed. In this regard, the device interface includes one or more control couplers. Each control coupler is adapted to a corresponding control of the audio system to be changed. The control sequencer provides a control sequence to the device interface that causes the control coupler(s) to vary the settings on the audio system. In practical applications, a combination of sequence values of the control sequence can represent a sufficiently high number of samples to determine a responsive behavior of the audio system.Type: ApplicationFiled: February 11, 2022Publication date: August 18, 2022Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Tuomas Juvela, Aleksi Tapani Peussa, Kimmo Erik Antero Rauhanen, Thomas William Sherson
-
Publication number: 20210166718Abstract: A neural network is trained to digitally model a reference audio system. Training is carried out by repeatedly performing a set of operations. The set of operations includes predicting by the neural network, a model output based upon an input, where the output approximates an expected output of the reference audio system, and the prediction is carried out in the time domain. The set of operations also includes applying a perceptual loss function to the neural network based upon a determined psychoacoustic property, wherein the perceptual loss function is applied in the frequency domain. Moreover, the set of operations includes adjusting the neural network responsive to the output of the perceptual loss function. A neural model file is output that can be loaded to generate a virtualization of the reference audio system.Type: ApplicationFiled: January 9, 2020Publication date: June 3, 2021Inventors: Douglas Andres Castro Borquez, Eero-Pekka Damskägg, Athanasios Gotsopoulos, Lauri Juvela, Thomas William Sherson