Abstract: This disclosure describes an apparatus and method of an embodiment of an invention that is a conferencing device that includes a microphone array that further comprises a plurality of microphones; a processor configured to execute the following steps: performing a beamforming operation to combine the plurality of microphones into a plurality of combined signals that is greater in number than one and less in number than the plurality of microphone signals, each of the plurality of combined signals corresponding to a different fixed beam; wherein performing the beamforming operation includes applying beamforming weights to the signals from each microphone to achieve a desired pickup pattern that includes a main lobe and sidelobes together with nulls for each fixed beam; performing an acoustic echo cancellation operation generate a plurality of combined echo cancelled signals; and selecting one or more of the combined echo cancelled signals for transmission to the far end.

Abstract: Examples of a textual entailment generation system are provided. The system obtains a query from a user and implements an artificial intelligence component to identify a premise, a word index, and a premise index associated with the query. The system may implement a first cognitive learning operation to determine a plurality of hypothesis and a hypothesis index corresponding to the premise. The system may generate a confidence index for each of the plurality of hypothesis based on a comparison of the hypothesis index with the premise index. The system may determine an entailment value, a contradiction value, and a neutral entailment value based on the confidence index for each of the plurality of hypothesis. The system may generate an entailment result relevant for resolving the query comprising the plurality of hypothesis along with the corresponding entailed output index.

Abstract: Implementations disclosed describe methods and systems to perform the methods of deploying and executing machine learning models on target-specific computational platforms. Optimization techniques include but are not limited to alignment of kernel operations with hardware instructions of a target processing device, reduction of kernel dimensions near boundaries of data, efficient reuse of a small number of memory components during neural network operations, run-time quantization of data and neural network parameters, and other methods.

Abstract: Implementations disclosed describe methods and systems to perform the methods of deploying and executing machine learning models on target-specific computational platforms. Optimization techniques include but are not limited to alignment of kernel operations with hardware instructions of a target processing device, reduction of kernel dimensions near boundaries of data, efficient reuse of a small number of memory components during neural network operations, run-time quantization of data and neural network parameters, and other methods.

Abstract: Implementations disclosed describe methods and systems to perform the methods of deploying and executing machine learning models on target-specific computational platforms. Optimization techniques include but are not limited to alignment of kernel operations with hardware instructions of a target processing device, reduction of kernel dimensions near boundaries of data, efficient reuse of a small number of memory components during neural network operations, run-time quantization of data and neural network parameters, and other methods.

Abstract: Example apparatus, systems and methods use a receiver of a first device to receive from a second device, radio frequency (RF) signals. Embodiments use a processor of the first device to determine, based on the RF signals, a set of angle-estimation values of an angle between a plurality of antenna elements of one of the first device and the second device and an antenna element of the other of the first device and the second device, and a set of confidence measurements. Each of the set of confidence measurements indicates a confidence of an angle-estimation value of the set of angle-estimation values.

Abstract: Embodiments of the present disclosure relate to an audio system for artificial reality applications. One or more transducers of the audio system output, in accordance with audio instructions, one or more ultrasonic pressure waves simulating a virtual audio source near an ear of a user of the headset. A controller of the audio system generates the audio instructions such that the one or more ultrasonic pressure waves form at least a portion of audio content for presentation to the user. An array of microphones of the audio system detects audio signals in a local area. A deep neural network of the audio system processes the detected audio signals to generate enhanced audio content, and the one or more transducers present the enhanced audio content to a user.

Abstract: An example method for pattern-based pruning of neural networks comprises: receiving, by a processing device, a plurality of feature maps produced by an input layer of a neural network; for each feature map of the plurality of feature maps, selecting, from a predetermined set of pruning masks, a pruning mask to be applied to the feature map; pruning the neural network by applying, to each feature map of the plurality of feature maps, a respective selected pruning mask to the feature map; and training the pruned neural network.

Abstract: This disclosure describes an apparatus and method of an embodiment of an invention that is a conferencing apparatus. This embodiment of the apparatus/system includes a microphone array that further comprises a plurality of microphones where each microphone is configured to sense acoustic waves and the plurality of microphones are oriented to develop a corresponding plurality of microphone signals; a processor, memory, and storage operably coupled to the microphone array, the processor configured to: perform a beamforming operation; perform an acoustic echo cancellation operation; perform a direction of arrival determination; and select one or more of the combined echo cancelled signals.

Abstract: Systems and methods provide a first sample of audio data and detect speech onset in the first sample of the audio data. Responsive to detecting the speech onset, systems and methods switch from capturing second samples of the audio data at first intervals, to capturing the second samples of the audio data at second intervals. Systems and methods provide contiguous audio data using the second samples of the audio data captured at the first intervals and at least one captured portion of the second samples of the audio data captured at the second intervals.

Abstract: Described herein are devices, methods, and systems for detecting a phrase from uttered speech. A processing device may determine a first model for phrase recognition based on a likelihood ratio using a set of training utterances. The set of utterances may be analyzed by the first model to determine a second model, the second model comprising a training state sequence for each of the set of training utterances, and wherein each training state sequence indicates a likely state for each time interval of a corresponding training utterance. A determination of whether a detected utterance corresponds to the phrase may be based on a concatenation of the first model and the second model.

Abstract: Techniques are disclosed for reducing the time required to read and write data to memory. Data reads and/or writes can be delayed when error correction code (ECC) bits, which are used to detect and/or correct data corruption, are written to memory. Writing ECC bits can take longer in some instances than writing data bits because an ECC write may involve a read/modify/write operation, as opposed to just simply writing the bits to memory. Some latencies associated with writing ECC bits can be hidden by interleaving ECC writes with data writes. However, if insufficient data writes are available for interleaving, hiding such latencies become difficult. Thus, various techniques are disclosed, for example, where ECC writes are deferred until a sufficient number of data writes become available for interleaving. By interleaving ECC writes, the disclosed techniques decrease the overall time required to read and write data to memory.

Abstract: Techniques for non-linear acoustic echo cancellation are described herein. In an embodiment, a system comprises a loudspeaker, a microphone array, a spatial filtering logic with a spatial filter, an acoustic echo canceller (AEC) logic and an adder logic block. The spatial filtering logic is configured to generate a spatially-filtered signal by applying the spatial filter using a reference signal sent to the loudspeaker and a multi-channel microphone signal from the microphone array. The generated spatially-filtered signal carries both linear echo and non-linear echo that are included in the multi-channel microphone signal. The AEC logic is configured to apply a linear adaptive filter using the spatially-filtered signal to generate a cancellation signal that estimates both the linear echo and the non-linear echo of the multi-channel microphone signal. The adder logic block is configured to generate an output signal based on the cancellation signal.

Abstract: Examples of a textual entailment generation system are provided. The system obtains a query from a user and implements an artificial intelligence component to identify a premise, a word index, and a premise index associated with the query. The system may implement a first cognitive learning operation to determine a plurality of hypothesis and a hypothesis index corresponding to the premise. The system may generate a confidence index for each of the plurality of hypothesis based on a comparison of the hypothesis index with the premise index. The system may determine an entailment value, a contradiction value, and a neutral entailment value based on the confidence index for each of the plurality of hypothesis. The system may generate an entailment result relevant for resolving the query comprising the plurality of hypothesis along with the corresponding entailed output index.

Abstract: Techniques for non-linear acoustic echo cancellation are described herein. In an embodiment, a system comprises a loudspeaker, a microphone array, a spatial filtering logic with a spatial filter, an acoustic echo canceler (AEC) logic and an adder logic block. The spatial filtering logic is configured to generate a spatially-filtered signal by applying the spatial filter using a reference signal sent to the loudspeaker and a multi-channel microphone signal from the microphone array. The generated spatially-filtered signal carries both linear echo and non-linear echo that are included in the multi-channel microphone signal. The AEC logic is configured to apply a linear adaptive filter using the spatially-filtered signal to generate a cancellation signal that estimates both the linear echo and the non-linear echo of the multi-channel microphone signal. The adder logic block is configured to generate an output signal based on the cancellation signal.

Abstract: Techniques for acoustic echo cancellation are described herein. In an example embodiment, a system comprises a speaker, a microphone array with multiple microphones, a beamformer (BF) logic and an acoustic echo canceller (AEC) logic. The speaker is configured to receive a reference signal. The BF logic is configured to receive audio signals from the multiple microphones and to generate a beamformed signal. The AEC logic is configured to receive the beamformed signal and the reference signal. The AEC logic is also configured to compute a vector of bias coefficients multiple times per time frame, to compute a background filter coefficient based on the vector of bias coefficients, to apply a background filter to the reference signal and the beamformed signal based on the background filter coefficient, to generate a background cancellation signal, and to generate an output signal based at least on the background cancellation signal.

Abstract: Example apparatus, systems and methods use a receiver of a first device to receive from a second device, radio frequency (RF) signals. Embodiments use a processor of the first device to determine, based on the RF signals, a set of angle-estimation values of an angle between a plurality of antenna elements of one of the first device and the second device and an antenna element of the other of the first device and the second device, and a set of confidence measurements. Each of the set of confidence measurements indicates a confidence of an angle-estimation value of the set of angle-estimation values.

Abstract: The present disclosure provides a flame retardant optical fiber cable. The flame retardant optical fiber cable includes a plurality of bundle binders. In addition, the flame retardant optical fiber cable includes a first layer, a second layer, a third layer, a fourth layer, a fifth layer, a sixth layer, a seventh layer and an eighth layer. The first layer surrounds a plurality of bundle binders. The second layer surrounds the first layer. The third layer surrounds the second layer. The fourth layer surrounds the third layer. The fifth layer surrounds the fourth layer. The sixth layer surrounds the fifth layer. The seventh layer surrounds the sixth layer. The eighth layer surrounds the seventh layer.

Abstract: Techniques are disclosed for reducing the time required to read and write data to memory. Data reads and/or writes can be delayed when error correction code (ECC) bits, which are used to detect and/or correct data corruption, are written to memory. Writing ECC bits can take longer in some instances than writing data bits because an ECC write may involve a read/modify/write operation, as opposed to just simply writing the bits to memory. Some latencies associated with writing ECC bits can be hidden by interleaving ECC writes with data writes. However, if insufficient data writes are available for interleaving, hiding such latencies become difficult. Thus, various techniques are disclosed, for example, where ECC writes are deferred until a sufficient number of data writes become available for interleaving. By interleaving ECC writes, the disclosed techniques decrease the overall time required to read and write data to memory.

Abstract: A method includes using a receiver of a first device, receiving from a second device, radio frequency (RF) signals. The method also includes using a processor of the first device, determining and storing, based on the RF signals, a set of angle-estimation values of an angle between a plurality of antenna elements of one of the first device and the second device and an antenna element of the other of the first device and the second device, a set of confidence measurements, and at least one of an Area-of Arrival (ARoA) value and an Area-of Departure (ARoD) value. Each of the set of confidence measurements indicates a confidence of an angle-estimation value of the set of angle-estimation values.