Patents by Inventor Raul Alejandro Casas
Raul Alejandro Casas 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).
-
Patent number: 11916686Abstract: Systems and methods are disclosed for audio group identification for conferencing. For example, methods may include joining a conference call using a network interface; accessing an audio signal that has been captured using a microphone; detecting a control signal in the audio signal; and, responsive to detection of the control signal, invoking modification of an audio path of the conference call.Type: GrantFiled: November 1, 2022Date of Patent: February 27, 2024Assignee: Cisco Technology, Inc.Inventors: Raul Alejandro Casas, Marcin Ciolek, Samer Hijazi, Dror Maydan, Hua Mu, Erik Panu, Christopher Rowen
-
Patent number: 11900677Abstract: Presented herein are systems and methods for generating a multi-view focused video stream. The methods involve obtaining at least one video stream of a first participant in an online video communication session between at least the first participant at a first endpoint and a second participant at a second endpoint; determining a bounding region of at least one element in the video stream; generating a focused video stream from the video stream that includes a focused view of the at least one element within the bounding region; and presenting the focused video stream on the second endpoint to at least the second participant.Type: GrantFiled: February 25, 2022Date of Patent: February 13, 2024Assignee: CISCO TECHNOLOGY, INC.Inventors: Hui-Ling Lu, Raul Alejandro Casas
-
Publication number: 20230421701Abstract: In one embodiment, an illustrative method herein may comprise: receiving, at a receiver, an audio codec stream; determining, by the receiver, a length of time associated with a look-ahead buffer of the audio codec stream; inputting, by the receiver, the audio codec stream into an audio enhancement model trained with one or more audio enhancements to cause the audio enhancement model to apply the one or more audio enhancements to the audio codec stream to generate an enhanced audio codec stream within the length of time associated with the look-ahead buffer of the audio codec stream; and outputting, by the receiver, the enhanced audio codec stream.Type: ApplicationFiled: May 20, 2022Publication date: December 28, 2023Inventors: Keith GRIFFIN, Samer Lutfi HIJAZI, Raul Alejandro CASAS, Yusuf Ziya ISIK
-
Publication number: 20230274544Abstract: Presented herein are systems and methods for generating a multi-view focused video stream. The methods involve obtaining at least one video stream of a first participant in an online video communication session between at least the first participant at a first endpoint and a second participant at a second endpoint; determining a bounding region of at least one element in the video stream; generating a focused video stream from the video stream that includes a focused view of the at least one element within the bounding region; and presenting the focused video stream on the second endpoint to at least the second participant.Type: ApplicationFiled: February 25, 2022Publication date: August 31, 2023Inventors: Hui-Ling Lu, Raul Alejandro Casas
-
Publication number: 20230129867Abstract: Systems and methods are disclosed for audio group identification for conferencing. For example, methods may include joining a conference call using a network interface; accessing an audio signal that has been captured using a microphone; detecting a control signal in the audio signal; and, responsive to detection of the control signal, invoking modification of an audio path of the conference call.Type: ApplicationFiled: November 1, 2022Publication date: April 27, 2023Inventors: Raul Alejandro Casas, Marcin Ciolek, Samer Hijazi, Dror Maydan, Hua Mu, Erik Panu, Christopher Rowen
-
Publication number: 20220392478Abstract: An endpoint selectively enhances a captured audio signal based on an operating mode. The endpoint obtains an audio input signal of multiple users in a physical location. The audio input signal is captured by a microphone. The endpoint separates voice signals from the audio input signal and determines an operating mode for an audio output signal. The endpoint selectively adjusts each of the voice signals based on the operating mode to generate the audio output signal.Type: ApplicationFiled: September 10, 2021Publication date: December 8, 2022Inventors: Samer Lutfi Hijazi, Christopher Rowen, Xuehong Mao, Ivana M. Balic, Raul Alejandro Casas, Savita Kini
-
Patent number: 11502860Abstract: Systems and methods are disclosed for audio group identification for conferencing. For example, methods may include joining a conference call using a network interface; accessing an audio signal that has been captured using a microphone; detecting a control signal in the audio signal; and, responsive to detection of the control signal, invoking modification of an audio path of the conference call.Type: GrantFiled: March 3, 2020Date of Patent: November 15, 2022Assignee: BabbleLabs LLCInventors: Raul Alejandro Casas, Samer Hijazi, Hua Mu, Marcin Ciolek, Dror Maydan, Christopher Rowen, Erik Panu
-
Patent number: 11132619Abstract: Some embodiments perform, in a multi-layer neural network in a computing device, a convolution operation on input feature maps with multiple convolutional filters. The convolutional filters have multiple filter precisions. In other embodiments, electronic design automation (EDA) systems, methods, and computer-readable media are presented for adding such a multi-layer neural network into an integrated circuit (IC) design.Type: GrantFiled: February 24, 2017Date of Patent: September 28, 2021Assignee: Cadence Design Systems, Inc.Inventors: Raúl Alejandro Casas, Samer Lutfi Hijazi, Piyush Kaul, Rishi Kumar, Xuehong Mao, Christopher Rowen
-
Publication number: 20210217436Abstract: Systems and methods are disclosed for audio enhancement. For example, methods may include accessing audio data; determining a window of audio samples based on the audio data; inputting the window of audio samples to a classifier to obtain a classification, in which the classifier includes a neural network and the classification takes a value from a set of multiple classes of audio; selecting, based on the classification, an audio enhancement network from a set of multiple audio enhancement networks; applying the selected audio enhancement network to the window of audio samples to obtain an enhanced audio segment, in which the selected audio enhancement network includes a neural network that has been trained using audio signals of a type associated with the classification; and storing, playing, or transmitting an enhanced audio signal based on the enhanced audio segment.Type: ApplicationFiled: March 25, 2021Publication date: July 15, 2021Inventors: Samer Hijazi, Xuehong Mao, Raul Alejandro Casas, Kamil Krzysztof Wojcicki, Dror Maydan, Christopher Rowen
-
Publication number: 20210144021Abstract: Systems and methods are disclosed for audio group identification for conferencing. For example, methods may include joining a conference call using a network interface; accessing an audio signal that has been captured using a microphone; detecting a control signal in the audio signal; and, responsive to detection of the control signal, invoking modification of an audio path of the conference call.Type: ApplicationFiled: March 3, 2020Publication date: May 13, 2021Inventors: Raul Alejandro Casas, Samer Hijazi, Hua Mu, Marcin Ciolek, Dror Maydan, Christopher Rowen, Erik Panu
-
Patent number: 10997502Abstract: Some embodiments perform, in a multi-layer neural network in a computing device, optimization of the multi-layer neural network, for example by making a convolutional change with a first plurality of convolutional filters, or by making a connection change of a first plurality of convolutional filters. In other embodiments, electronic design automation (EDA) systems, methods, and computer-readable media are presented for adding such a multi-layer neural network into an integrated circuit (IC) design.Type: GrantFiled: April 13, 2017Date of Patent: May 4, 2021Assignee: Cadence Design Systems, Inc.Inventors: Raúl Alejandro Casas, Samer Lutfi Hijazi, Piyush Kaul, Rishi Kumar, Xuehong Mao, Christopher Rowen
-
Patent number: 10991379Abstract: Systems and methods are disclosed for audio enhancement. For example, methods may include accessing audio data; determining a window of audio samples based on the audio data; inputting the window of audio samples to a classifier to obtain a classification, in which the classifier includes a neural network and the classification takes a value from a set of multiple classes of audio; selecting, based on the classification, an audio enhancement network from a set of multiple audio enhancement networks; applying the selected audio enhancement network to the window of audio samples to obtain an enhanced audio segment, in which the selected audio enhancement network includes a neural network that has been trained using audio signals of a type associated with the classification; and storing, playing, or transmitting an enhanced audio signal based on the enhanced audio segment.Type: GrantFiled: June 22, 2018Date of Patent: April 27, 2021Assignee: BabbleLabs LLCInventors: Samer Hijazi, Xuehong Mao, Raul Alejandro Casas, Kamil Krzysztof Wojcicki, Dror Maydan, Christopher Rowen
-
Patent number: 10534994Abstract: The present disclosure relates to a computer-implemented method for analyzing one or more hyper-parameters for a multi-layer computational structure. The method may include accessing, using at least one processor, input data for recognition. The input data may include at least one of an image, a pattern, a speech input, a natural language input, a video input, and a complex data set. The method may further include processing the input data using one or more layers of the multi-layer computational structure and performing matrix factorization of the one or more layers. The method may also include analyzing one or more hyper-parameters for the one or more layers based upon, at least in part, the matrix factorization of the one or more layers.Type: GrantFiled: November 11, 2015Date of Patent: January 14, 2020Assignee: Cadence Design Systems, Inc.Inventors: Piyush Kaul, Samer Lutfi Hijazi, Raul Alejandro Casas, Rishi Kumar, Xuehong Mao, Christopher Rowen
-
Publication number: 20190392852Abstract: Systems and methods are disclosed for audio enhancement. For example, methods may include accessing audio data; determining a window of audio samples based on the audio data; inputting the window of audio samples to a classifier to obtain a classification, in which the classifier includes a neural network and the classification takes a value from a set of multiple classes of audio; selecting, based on the classification, an audio enhancement network from a set of multiple audio enhancement networks; applying the selected audio enhancement network to the window of audio samples to obtain an enhanced audio segment, in which the selected audio enhancement network includes a neural network that has been trained using audio signals of a type associated with the classification; and storing, playing, or transmitting an enhanced audio signal based on the enhanced audio segment.Type: ApplicationFiled: June 22, 2018Publication date: December 26, 2019Inventors: Samer Hijazi, Xuehong Mao, Raul Alejandro Casas, Kamil Krzysztof Wojcicki, Dror Maydan, Christopher Rowen
-
Patent number: 10290107Abstract: Aspects of the present disclosure involve a transform domain regression convolutional neural network for image segmentation. Example embodiments include a system comprising a machine-readable storage medium storing instructions and computer-implemented methods for classifying one or more pixels in an image. The method may include analyzing the image to estimate one or more transform domain coefficients using a multi-layered function such as a convolutional neural network. The method may further include generating a segmented image by applying a change of basis transformation to the estimated one or more transform domain coefficients.Type: GrantFiled: June 19, 2017Date of Patent: May 14, 2019Assignee: Cadence Design Systems, Inc.Inventors: Raúl Alejandro Casas, Samer Lutfi Hijazi, Rishi Kumar, Piyush Kaul, Xuehong Mao, Christopher Rowen, Himanshu Charaya
-
Patent number: 8724759Abstract: The current application is directed to maintaining the correct number of symbols in a protocol frame in a digital communications receiver, to prevent catastrophic failure due to dynamic multipath or cycle slips. Timing recovery and framing are coherent, facilitated by placing channel estimation directly into a larger timing recovery loop.Type: GrantFiled: May 7, 2012Date of Patent: May 13, 2014Assignee: I Berium Communications, Inc.Inventors: Raúl Alejandro Casas, Stephen Biracree, Anand Mahendra Shah, Slobodan Simovich, Thomas Joseph Endres
-
Publication number: 20140047497Abstract: The current document is related to the equalization of digital communications signals, including GB 20600-2006 and ATSC digital television signals, and is directed to methods that initialize adaptive filters for processing payload data within equalizers. These methods may operate at a clock speed faster than the symbol transmission rate and are applicable to a multitude of digital communications standards and protocols. In certain implementations, the initialization method generates input records, from output of a pseudorandom number generator, and output records, from the output of a pseudorandom number generator and a channel estimate, that are decoupled from transmitted and received data and are used to adjust equalizer coefficients to an initialization setting suitable for processing payload data.Type: ApplicationFiled: August 12, 2013Publication date: February 13, 2014Applicant: Iberium Communications, Inc.Inventors: Raul Alejandro Casas, Stephen Leonard Biracree, Slobodan Simovich, Thomas Joseph Endres
-
Patent number: 8643775Abstract: Certain embodiments of the present invention encapsulate a variety of data, for example, FIC data, together with ATSC-M/H Service data, into a single IP stream, to simplify the interface between demodulator and media processor. A single data interface protocol within the receiver can then be used, facilitating integration.Type: GrantFiled: April 14, 2011Date of Patent: February 4, 2014Assignee: Iberium Communications Inc.Inventors: Anand Mahendra Shah, Stephen Biracree, Raúl Alejandro Casas, Slobodan Simovich, Thomas Joseph Endres
-
Publication number: 20130101010Abstract: The current application is directed to joint decoding and equalization using a decision feedback equalizer. An example method to which the current application and certain of the current claims are directed uses joint trellis decoding and decision feedback equalization to efficiently estimate non-contiguous symbols using non-contiguous equalizer outputs. The estimation process uses all new possibilities of symbol values, rather than old decision feedback symbol estimates.Type: ApplicationFiled: April 17, 2012Publication date: April 25, 2013Inventors: Raúl Alejandro Casas, Stephen Leonard Biracree, Slobodan Simovich, Thomas Joseph Endres, Anand Mahendra Shah
-
Publication number: 20120281140Abstract: The current application is directed to maintaining the correct number of symbols in a protocol frame in a digital communications receiver, to prevent catastrophic failure due to dynamic multipath or cycle slips. Timing recovery and framing are coherent, facilitated by placing channel estimation directly into a larger timing recovery loop.Type: ApplicationFiled: May 7, 2012Publication date: November 8, 2012Inventors: Raul Alejandro Casas, Stephen Biracree, Anand Mahendra Shah, Slobodan Simovich, Thomas Joseph Endres