Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map including a plurality of pixels, each of the pixels being labeled with a corresponding class of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; applying inference to generate a plurality of ranked labels based on the area ratios; and outputting a detected dominant class of the scene based on the plurality of ranked labels.

Abstract: A method of depth detection based on a plurality of video frames includes receiving a plurality of input frames including a first input frame, a second input frame, and a third input frame respectively corresponding to different capture times, convolving the first to third input frames to generate a first feature map, a second feature map, and a third feature map corresponding to the different capture times, calculating a temporal attention map based on the first to third feature maps, the temporal attention map including a plurality of weights corresponding to different pairs of feature maps from among the first to third feature maps, each weight of the plurality of weights indicating a similarity level of a corresponding pair of feature maps, and applying the temporal attention map to the first to third feature maps to generate a feature map with temporal attention.

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method includes training a conditional autoencoder using a Lagrange multiplier and training a neural network that includes the conditional autoencoder with mixed quantization bin sizes.

Abstract: A method for performing echo cancellation includes: receiving a far-end signal from a far-end device at a near-end device; recording a microphone signal at the near-end device including: a near-end signal; and an echo signal corresponding to the far-end signal; extracting far-end features from the far-end signal; extracting microphone features from the microphone signal; computing estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including: an echo estimator including a first stack of a recurrent neural network configured to compute estimated echo features based on the far-end features; and a near-end estimator including a second stack of the recurrent neural network configured to compute the estimated near-end features based on an output of the first stack and the microphone signal; computing an estimated near-end signal from the estimated near-end features; and transmitting the estimated near-end signal to the far-end device.

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method includes training a conditional autoencoder using a Lagrange multiplier and training a neural network that includes the conditional autoencoder with mixed quantization bin sizes.

Abstract: Apparatuses (including user equipment (UE) and modem chips for UEs), systems, and methods for UE downlink Hybrid Automatic Repeat reQuest (HARQ) buffer memory management are described. In one method, the entire UE DL HARQ buffer memory space is pre-partitioned according to the number and capacities of the UE's active carrier components. In another method, the UE DL HARQ buffer is split between on-chip and off-chip memory so that each partition and sub-partition is allocated between the on-chip and off-chip memories in accordance with an optimum ratio.

Abstract: A method and system for providing Gaussian weighted self-attention for speech enhancement are herein provided. According to one embodiment, the method includes receiving a input noise signal, generating a score matrix based on the received input noise signal, and applying a Gaussian weighted function to the generated score matrix.

Abstract: An apparatus and a method. The apparatus includes a plurality of long short term memory (LSTM) networks, wherein each of the plurality of LSTM networks is at a different network layer, wherein each of the plurality of LSTM networks is configured to determine a residual function, wherein each of the plurality of LSTM networks includes an output gate to control what is provided to a subsequent LSTM network, and wherein each of the plurality of LSTM networks includes at least one highway connection to compensate for the residual function of a previous LSTM network.

Abstract: A method and system for determining depth information of an image are herein provided. According to one embodiment, the method includes receiving an image input, classifying the input image into a depth range of a plurality of depth ranges, and determining a depth map of the image by applying depth estimation based on the depth range into which the input image is classified.

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

Abstract: A method for performing echo cancellation includes: receiving a far-end signal from a far-end device at a near-end device; recording a microphone signal at the near-end device including: a near-end signal; and an echo signal corresponding to the far-end signal; extracting far-end features from the far-end signal; extracting microphone features from the microphone signal; computing estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including: an echo estimator including a first stack of a recurrent neural network configured to compute estimated echo features based on the far-end features; and a near-end estimator including a second stack of the recurrent neural network configured to compute the estimated near-end features based on an output of the first stack and the microphone signal; computing an estimated near-end signal from the estimated near-end features; and transmitting the estimated near-end signal to the far-end device.

Abstract: A system for performing echo cancellation includes: a processor configured to: receive a far-end signal; record a microphone signal including: a near-end signal; and an echo signal corresponding to the far-end signal; extract far-end features from the far-end signal; extract microphone features from the microphone signal; compute estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including a recurrent neural network including: an encoder including a plurality of gated recurrent units; and a decoder including a plurality of gated recurrent units; compute an estimated near-end signal from the estimated near-end features; and transmit the estimated near-end signal to the far-end device. The recurrent neural network may include a contextual attention module; and the recurrent neural network may take, as input, a plurality of error features computed based on the far-end features, the microphone features, and acoustic path parameters.

Abstract: A method for performing echo cancellation includes: receiving a far-end signal from a far-end device at a near-end device; recording a microphone signal at the near-end device including: a near-end signal; and an echo signal corresponding to the far-end signal; extracting far-end features from the far-end signal; extracting microphone features from the microphone signal; computing estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including: an echo estimator including a first stack of a recurrent neural network configured to compute estimated echo features based on the far-end features; and a near-end estimator including a second stack of the recurrent neural network configured to compute the estimated near-end features based on an output of the first stack and the microphone signal; computing an estimated near-end signal from the estimated near-end features; and transmitting the estimated near-end signal to the far-end device.

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method includes training a conditional autoencoder using a Lagrange multiplier and training a neural network that includes the conditional autoencoder with mixed quantization bin sizes.

Abstract: A method and an apparatus are provided. The method includes receiving a video with a first plurality of frames having a first resolution; generating a plurality of warped frames from the first plurality of frames based on a first type of motion compensation; generating a second plurality of frames having a second resolution, wherein the second resolution is of higher resolution than the first resolution, wherein each of the second plurality of frames having the second resolution is derived from a subset of the plurality of warped frames using a convolutional network; and generating a third plurality of frames having the second resolution based on a second type of motion compensation, wherein each of the third plurality of frames having the second resolution is derived from a fusing a subset of the second plurality of frames.

Abstract: A method and apparatus for providing a rotational invariant neural network is herein disclosed. According to one embodiment, a method includes receiving a first input of an image in a first orientation and training a kernel to be symmetric such that an output corresponding to the first input is the same as an output corresponding to a second input of the image in a second orientation.

Abstract: A method and an apparatus are provided. The method includes receiving a video with a first plurality of frames having a first resolution; generating a plurality of warped frames from the first plurality of frames based on a first type of motion compensation; generating a second plurality of frames having a second resolution, wherein the second resolution is of higher resolution than the first resolution, wherein each of the second plurality of frames having the second resolution is derived from a subset of the plurality of warped frames using a convolutional network; and generating a third plurality of frames having the second resolution based on a second type of motion compensation, wherein each of the third plurality of frames having the second resolution is derived from a fusing a subset of the second plurality of frames.

Abstract: An image denoising neural network training architecture includes an image denoising neural network and a clean data neural network, and the image denoising neural network and clean data neural network share information between each other.

Abstract: A method and system for providing end-to-end multi-task denoising for joint signal distortion ratio (SDR) and perceptual evaluation of speech quality (PESQ) optimization is herein disclosed. According to one embodiment, an method includes receiving a noisy signal, generating a denoised output signal, determining a signal distortion ratio (SDR) loss function based on the denoised output signal, determining a perceptual evaluation of speech quality (PESQ) loss function based on the denoised output signal, and optimizing an overall loss function based on the PESQ loss function and the SDR loss function.