Abstract: A technique to program a compute channel having multiple computational circuit blocks coupled in series in a pipeline can include receiving a machine instruction for the compute channel. The machine instruction is decoded to obtain an opcode, and the opcode can be used as an index to access an opcode entry in an opcode table. The opcode entry contains a pointer to a microoperation, and the pointer can be used to access a microoperation represented by a control entry in a control table and a datapath configuration entry in a datapath table. The microoperation can then be issued to the compute channel by configuring the compute channel with the control entry and the datapath configuration entry.

Abstract: A wearable device may compress the skin of a user when worn, which may affect values determined using sensors of the device. To determine the effect of skin compression on the values, a time-of-flight signal, images, or frames of video data that depict a portion of the body having indentations from wearing the device may be acquired. Characteristics of the images, such as shadows associated with the indentations, may be processed using a machine learning algorithm or mathematical function to determine a depth of various portions of the indentations. Depth data from the time of flight signal may be used to refine or modify these determined depths. The amount of skin compression associated with the indentations may be used to modify signals acquired using sensors, or output a recommendation for a band or other method for securing the device.

Abstract: A system configured to improve audio processing by performing dereverberation and noise reduction during a communication session. In some examples, the system may include a deep neural network (DNN) configured to perform speech enhancement, which is located after an Acoustic Echo Cancellation (AEC) component. For example, the DNN may process isolated audio data output by the AEC component to jointly mitigate additive noise and reverberation. In other examples, the system may include a DNN configured to perform acoustic interference cancellation, which may jointly mitigate additive noise, reverberation, and residual echo, removing the need to perform residual echo suppression processing. The DNN is configured to process complex-valued spectrograms corresponding to the isolated audio data and/or estimated echo data generated by the AEC component.

Abstract: Distributed orchestration of data retrieval for generative machine learning model may be performed. When a natural language request to perform a natural language task is received that is associated with a generative application, one or more data retrievers may be selected to access associated data repositories according to a previously specified retrieval configuration for the generative natural language application. The data may then be obtained by the selected data retrievers and used to generate a prompt to a generative machine learning model. A result of the generative machine learning model may then be used to provide a response to the natural language request to perform the natural language task.

Abstract: A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

Abstract: An index is created with split documents to retrieve and augment generation of a response to a natural language request using a generative machine learning model. When a natural language request is received, a search representation is generated and used to retrieve candidate portions of documents from the index. A relevancy ranking is performed to identify relevant portions of documents from the candidates and provide the relevant portions to prompt a generative machine learning model to provide a result for the natural language request.

Abstract: Template-based tuning is performed on a generative machine learning model where a shared template is used to tune the generative machine learning model across multiple natural language tasks. When a natural language request to perform a natural language task is received, portions of a shared template to complete are identified as part of generating a prompt. The generative machine learning model is instructed according to the generated prompt and a response to the request is returned based on a result of the generative machine learning model.

Abstract: Intent classification is performed for executing a retrieval augmented generation pipeline for natural language tasks using a generative machine learning model. A natural language generative application with associated data repositories may submit a natural language task. A classification machine learning model is used to determine an intent for the natural language request. A number of iterations of a retrieval pipeline may be determined to perform the natural language task based on the intent. The natural language request may be processed through a retrieval pipeline according to the determined number of iterations before returning a result to the request.

Abstract: A block-based storage system hosts logical volumes that are implemented via multiple replicas of volume data stored on multiple resource hosts in different failure domains. Also, the block-based storage service allows multiple client computing devices to attach to a same given logical volume at the same time. In order to prevent unnecessary failovers, a primary node storing a primary replica is configured with a health check application programmatic interface (API) and a secondary node storing a secondary replica determines whether or not to initiate a failover based on the health of the primary replica.

Abstract: Technologies directed to performing switchover across Internet service providers in a last-mile network are described. One method includes receiving, by a first wireless device, a destination address, a first network address of a first network addressing scheme, and a first message. The method further includes determining a first status of at least one of a first NSP or a second NSP. The first NSP uses a second network addressing scheme and the second NSP uses a third network addressing scheme. The method further includes determining a second network address of the third network addressing scheme. The method further includes sending, using the second NSP the second network address and the first message. The method further includes determining a third network address of a fourth network addressing scheme and sending to a fourth wireless device corresponding to the destination address the third network address and the first message.

Abstract: Captures or recordings of sensitive information or data displayed on screens or displays are detected by generating unique identifiers of users and embedding linked codes including such identifiers into the information or data. When the information or data is accessed by a user and displayed on a screen, and an image of the information or data is captured by a camera of a mobile device or other system, the camera detects a code within the images and requests to access a page or other networked resource associated with a link embedded in the code. Upon detecting a request to access such a page, the request may be attributed to the user. Upon detecting a unique identifier within an image depicting sensitive information, the image may be attributed to the user.

Abstract: A system may provide a voice user interface (VUI) for sending a media comment (e.g., brief clips of audio data representing speech) to a media content creator such as a podcaster, talk show, music app, etc. The system can identify a destination for the media comment based on context (e.g., an identifier corresponding to media content currently or recently output by a user device) and/or via voice dialog with the user. Content creators can invite, receive, and play users' media comments on the show, thereby increasing audience engagement. A media comment may include a request for or dedication of a song, a “shout out” to another listener, a story/opinion, a question, a response to a poll, a contest entry, etc.

Abstract: A determination is made that anomaly analysis is to be performed with respect to an application. An anomaly score of the application is generated with respect to observed values of a plurality of metrics of the application. Generation of the anomaly score comprises computing an anomaly score contribution associated with an analysis of a correlation between values of a pair of metrics of the application. In response to a detection that the anomaly score exceeds a threshold, an anomaly response operation is initiated.

Abstract: A speech interface device is configured with “hybrid” capabilities, which allows the speech interface device to perform actions in response to user speech, even when the speech interface device is unable to communicate with a remote system over a wide area network (e.g., the Internet). A hybrid request selector of the speech interface device sends audio data representing user speech to both a remote speech processing system and a local speech processing component executing on the speech interface device, and then waits for a response from either or both components. The local speech processing component may start execution based on the audio data and subsequently suspend the execution until further instruction from the hybrid request selector. The hybrid request selector can then determine which response to use, and, depending on which response is chosen, may instruct the local speech processing component to either continue or terminate the suspended execution.

Abstract: The present disclosure presents wall-mounted near field communication systems and related methods. One such system comprises a sign assembly having a near field communication (NFC) tag comprising a first conducting member, a substrate assembly having a weakness area, wherein the substrate assembly comprises a plastic substrate; and first adhesive securing the NFC tag device to the substrate assembly such that the first conducting member is disposed proximate the weakness area.