Cisco Technology, Inc.

Cadence Design Systems, Inc.

Babblelabs LLC

Xuehong Mao

Samer Lutfi Hijazi

Christopher Rowen

Raul Alejandro Casas

Rishi Kumar

Piyush Kaul

Raúl Alejandro Casas

Yusuf Ziya Isik

Amir Salah Abdelsamie Abdelwahed

Ivana M Balic

Kamil Krzysztof Wojcicki

Dror E Maydan

David Guoqing Zhang

Dror Maydan

Himanshu Charaya

In one example embodiment, speech signals are received from a user during a communication session. The received speech signals contain noise including speech of other individuals. The received speech signals are transformed by a machine learning model to produce transformed speech signals corresponding to the received speech signals with a reduced amount of the noise. The machine learning model is trained with speech of the user satisfying a noise threshold and collected during one or more communication sessions.

Transforming speech signals to attenuate speech of competing individuals and other noise

In some aspects, the techniques described herein relate to a method including: encoding a current data portion to generate an encoded current data portion for inclusion in a data packet; encoding, based upon content of the current data portion, a forward error correction data portion for a previous data portion to generate an encoded forward error correction data portion; generating the data packet including the encoded current data portion and the encoded forward error correction data portion; and providing the data packet to a receiver.

Bandwidth utilization techniques for in-band redundant data

In some aspects, the techniques described herein relate to a method including: obtaining data to be compressed; determining a distance between the data to be compressed and each codeword of a plurality of codewords; selecting a predetermined number of codewords of the plurality of codewords based on the distance between the data to be compressed and each of the predetermined number of codewords; and generating compressed data, where the compressed data includes an indication of the predetermined number of codewords of the plurality of codewords.

Computationally efficient and bitrate scalable soft vector quantization

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.

Data driven audio enhancement

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.

Filtering in trainable networks

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.

Complexity optimization of trainable networks

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.

System and method for hyper-parameter analysis for multi-layer computational structures

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.

Growing community of inventors

San Jose, CA, United States of America

Xuehong Mao