Abstract: A data-driven audio codec system that involves producing multiple compressed streams comprising encoded information (e.g., codeword indices) at different time scales (time intervals or frequency). This may allow for separation of different properties of speech, such as content and aspects of style (prosody), into the different compressed streams without explicitly enforcing it, i.e., in an unsupervised manner. Speech audio is encoded to produce a plurality of encoded streams comprising encoded information for the speech audio at different time scales. The plurality of encoded streams are decoded to generate output audio.

Abstract: A method of performing packet loss concealment in a neural audio encoder/decoder (codec) system. The method includes receiving an indication of a lost audio packet at a receive side of a neural network audio codec system that includes an audio encoder and an audio decoder, wherein the lost audio packet comprises an index of a codeword that is representative of a portion of speech audio presented to the audio encoder, predicting the index of the codeword in the lost packet to obtain a predicted index, deriving a predicted embedding vector from the predicted index, and decoding, by the audio decoder, the embedding vector to generate an audio output.

Abstract: A neural network audio codec system and related methods are provided. In one example, a method is provided comprising: obtaining speech audio to be encoded; applying the speech audio to an audio encoder that is part of a neural network audio codec system that includes the audio encoder and an audio decoder. The audio encoder and the audio decoder have been trained in an end-to-end manner. The speech audio is encoded with the audio encoder to generate embedding vectors that represent a snapshot of speech audio attributes over successive timeframes of the raw speech audio, and from the embedding vectors, codeword indices are generated to entries in a codebook. The codeword indices are then transmitted or stored for later retrieval and processing by the audio decoder.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method allocates bandwidth from a radio frequency spectrum in a cellular network including a set of cells. Each cell includes a base station for serving a set of mobile stations in the cell. An area around each base station is partitioned into a center region and an edge region. In each base station, cell-center bandwidth for use by the mobile stations in the center region is reserved according to an inter-cell interference coordination (ICIC) protocol, and cell-edge bandwidth for use by the mobile stations in the edge region is reserved according to the ICIC protocol. The bandwidth can be fixed or adaptive to reduce the signaling overhead. The adaptive bandwidth can be further partitioned into reserved and the free bands. Mobile stations are classified as primary and secondary users, depending on whether they use or are assigned the fixed or adaptive band radio resources.