Abstract: Techniques and apparatuses are described that perform audioplethysmography calibration. Provided according to one or more preferred embodiments is a hearable, such as an earbud, that is capable of performing a novel physiological monitoring process termed herein audioplethysmography, an active acoustic method capable of sensing subtle physiologically-related changes observable at a user's outer and middle ear. The hearable can utilize audioplethysmography to monitor a user's biometrics, recognize facial behaviors, and/or sense an environment using acoustic signals. The techniques for audioplethysmography calibration enable the hearable to dynamically select frequencies that improve the performance of audioplethysmography. With audioplethysmography calibration, the hearable may utilize different frequencies for different ears and these frequencies may change over time.

Abstract: A method for a statistics collection framework includes receiving a schema defining a relational database for storing a plurality of statistics corresponding to a query, the relational database including a plurality of data tables relationally connected according to the schema, each data table of the plurality of data tables corresponding to a respective statistic. The method includes receiving a query corresponding to data at a data store. The method also includes executing the query. During execution of the query, the method includes collecting, from a query execution database, the plurality of statistics related to the query, each statistic of the plurality of statistics corresponding to a respective data table of the plurality of data tables of the relational database and, for each statistic of the plurality of statistics, storing the respective statistic at the respective data table according to the schema.

Abstract: This document describes systems for and techniques of alternating-current (AC) power harmonic-based circuit state detection. In various aspects, a system includes a component, a bypass circuit for the component, and a controller with an AC power harmonic-based circuit state detector that can determine a state of the bypass circuit. The AC power harmonic-based circuit state detector may convert an AC voltage of the AC power to a direct current (DC) voltage, filter the DC voltage to obtain a voltage of a harmonic of the AC power, and compare the voltage of the harmonic to a threshold to determine that the bypass circuit is in a fault state (blown fuse). By so doing, the controller of the system can notify a user that the bypass circuit needs to be reset or replaced to reenable operation of the system and avoid poor user experience typically associated with a non- or mis-functioning system.

Abstract: A method includes obtaining training data including a plurality of training audio signals and corresponding transcripts. Each training audio signal is spoken by a target speaker in a first accent/dialect. For each training audio signal of the training data, the method includes generating a training synthesized speech representation spoken by the target speaker in a second accent/dialect different than the first accent/dialect and training a text-to-speech (TTS) system based on the corresponding transcript and the training synthesized speech representation. The method also includes receiving an input text utterance to be synthesized into speech in the second accent/dialect. The method also includes obtaining conditioning inputs that include a speaker embedding and an accent/dialect identifier that identifies the second accent/dialect.

Abstract: A method includes receiving training data that includes unspoken text utterances and un-transcribed non-synthetic speech utterances. Each unspoken text utterance is not paired with any corresponding spoken utterance of non-synthetic speech. Each un-transcribed non-synthetic speech utterance is not paired with a corresponding transcription. The method also includes generating a corresponding synthetic speech representation for each unspoken textual utterance of the received training data using a text-to-speech model. The method also includes pre-training an audio encoder on the synthetic speech representations generated for the unspoken textual utterances and the un-transcribed non-synthetic speech utterances to teach the audio encoder to jointly learn shared speech and text representations.

Abstract: A method for golden prompt generation based on authoritative publications includes receiving an initial authoritative publication associated with a specific topic. The method includes retrieving, using the initial authoritative publication additional authoritative publications associated with the specific topic. The method includes generating, using natural language processing, a set of golden prompts from the set of authoritative publications. Each golden prompt of the set of golden prompts includes text from the set of authoritative publications. The method includes fine-tuning a pre-trained model using the set of authoritative publications. The method includes generating, using the fine-tuned model and the set of golden prompts, a set of predictions. The method includes determining, using the set of predictions and the set of authoritative publications, an error rate of the fine-tuned model. The error rate indicates a similarity between the set of predictions and the set of authoritative publications.

Abstract: A method includes training, using an un-supervised learning technique, an auxiliary ASR model based on a first set of un-transcribed source task speech utterances to determine a first task vector, training, using the un-supervised learning technique, the auxiliary ASR model based on a second set of un-transcribed speech utterances to determine a second task vector, and training, using the un-supervised learning technique, the auxiliary ASR model based on un-transcribed target task speech utterances to determine a target task vector. The method also includes determining a first correlation between the first and target task vectors, determining a second correlation between the second and target task vectors, and adapting parameters of a trained primary ASR model based on the first and second source task vectors and the first and second correlations to teach the primary ASR model to learn how to recognize speech associated with the target task.

Abstract: A method includes receiving a sequence of acoustic frames characterizing a spoken utterance in a particular native language. The method also includes generating a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames by a causal encoder that includes an initial stack of multi-head attention layers. The method also includes generating a second higher order feature representation for a corresponding first higher order feature representation by a non-causal encoder that includes a final stack of multi-head attention layers. The method also includes receiving, as input at each corresponding language-dependent adapter (LDA) module, a language ID vector identifying the particular native language to activate corresponding language-dependent weights specific to the particular native language. The method also includes generating a first probability distribution over possible speech recognition hypotheses by a decoder.

Abstract: Various arrangements are presented for performing a hierarchical application launch of an application. A requests to register one or more smart home devices can be received in association with a user account. The smart home devices can be mapped to the user account based on receiving the requests. An application that is mapped to the user account may be launched; the application can analyze the one or more smart home devices registered to the user account and a user interface hierarchy. Based on analyzing the one or more smart home devices registered to the user account and the user interface hierarchy, an initial launch interface can be selected and output for presentation.

Abstract: A method includes receiving training data that includes a plurality of sets of training utterances each associated with a respective language. Each training utterance includes a corresponding reference speech representation paired with a corresponding input text sequence. For each training utterance, the method includes generating a corresponding encoded textual representation for the corresponding input text sequence, generating a corresponding speech encoding for the corresponding reference speech representation, generating a shared encoder output, and determining a text-to-speech (TTS) loss based on the corresponding encoded textual representation, the corresponding speech encoding, and the shared encoder output. The method also includes training a TTS model based on the TTS losses determined for the training utterances in each set of the training utterances to teach the TTS model to learn how to synthesize speech in each of the respective languages.

Abstract: This document describes a vapor chamber within an electronic device. In aspects, an electronic device includes a middle frame that provides mechanical support for the electronic device, a middle plate affixed to the middle frame to define an inner layer of a chassis, and a vapor chamber disposed inside the middle plate. The vapor chamber includes a first region proximate to a heat source and a second region opposite the first region. A coolant is evaporated in a first mode at the first region by heat absorbed from the heat source and is condensed in a second mode in the second region. This vapor chamber permits cooling of elements within the electronic device at lower cost and/or smaller size than many conventional cooling systems.

Abstract: This document describes techniques and devices for a radar recognition-aided search. Through use of a radar-based recognition system, gestures made by, and physiological information about, persons can be determined. In the case of physiological information, the techniques can use this information to refine a search. For example, if a person requests a search for a coffee shop, the techniques may refine the search to coffee shops in the direction that the person is walking. In the case of a gesture, the techniques may refine or base a search solely on the gesture. Thus, a search for information about a store, car, or tree can be made responsive to a gesture pointing at the store, car, or tree with or without explicit entry of a search query.

Abstract: This document describes methods and systems of adaptive fingerprint-enrollment to finger characteristics using local under-display fingerprint sensors, UDFPS, in an electronic device. The electronic device includes an adaptive-enrollment module that determines characteristics of a fingerprint based on information corresponding to a touch input detected by a touch-display device, including size and shape of an area of the touch input. Based on the fingerprint characteristics, a number and location of enrollment touches used for completing enrollment of the fingerprint are adjusted to minimize the number of enrollment touches required to complete the enrollment, minimize the amount of time needed to complete the enrollment, and maximize coverage of the fingerprint.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for receiving user input that defines a search query, and providing the search query to a server system. Information that a search engine system determined was responsive to the search query is received at a computing device. The computing device is identified as in a first state, and a first output mode for audibly outputting at least a portion of the information is selected. The first output mode is selected from a collection of the first output mode and a second output mode. The second output mode is selected in response to the computing device being in a second state and is for visually outputting at least the portion of the information and not audibly outputting the at least portion of the information. At least the portion of information is audibly output.

Abstract: A method includes receiving audio data corresponding to an utterance spoken by a particular user and captured in streaming audio by a user device. The method also includes performing speaker identification on the audio data to identify an identity of the particular user that spoke the utterance. The method also includes obtaining a keyword detection model personalized for the particular user based on the identity of the particular user that spoke the utterance. The keyword detection model is conditioned on speaker characteristic information associated with the particular user to adapt the keyword detection model to detect a presence of a keyword in audio for the particular user. The method also includes determining that the utterance includes the keyword using the keyword detection model personalized for the particular user.

Abstract: A method includes obtaining a plurality of training samples that each include a respective speech utterance and a respective textual utterance representing a transcription of the respective speech utterance. The method also includes fine-tuning, using quantization and sparsity aware training with native integer operations, a pre-trained automatic speech recognition (ASR) model on the plurality of training samples. Here, the pre-trained ASR model includes a plurality of weights and the fine-tuning includes pruning one or more weights of the plurality of weights using a sparsity mask and quantizing each weight of the plurality of weights based on an integer with a fixed-bit width. The method also includes providing the fine-tuned ASR model to a user device.

Abstract: A method executed on data processing hardware and including displaying, on a display in communication with the data processing hardware, a user interface for a chat session between a user and a chatbot, the user interface including a plurality of entries input by the user and a plurality of corresponding responses from the chatbot. The method also includes receiving, in the user interface, a user input indication indicating selection of a particular entry of the plurality of entries, the particular entry being other than a last entry of the plurality of entries. The method further includes receiving, in the user interface, a new entry input by the user for an additional entry associated with the particular entry. The method additionally includes based on the additional entry associated with the particular entry, causing the chatbot to update one or more of the plurality of corresponding responses from the chatbot.

Abstract: A method includes obtaining, from a user device associated with a user, an audio signature, the audio signature extracted from audio data corresponding to a query spoken by the user. The method also includes processing, using a neural network, the audio signature to identify document tokens that match the audio signature within a shared embedding space, the neural network trained to jointly embed audio signatures and document tokens in the shared embedding space. The method also includes retrieving, using the document tokens and the shared embedding space, a set of search results for the query, and providing, for output from the user device, one or more search results from the set of search results to the user.

Abstract: A method includes receiving, from a user, an embedded application view request requesting embedding of an application view within a host container. The application view is derived from a no-code application, and the no-code application is generated using a no-code application development environment. The embedded application view request includes a uniform resource locator (URL) referencing the no-code application and a data record of a dataset associated with the no-code application. The method includes obtaining credentials associated with the user and determining, using the credentials, that the user has access to the data record of the dataset. The method also includes, after determining that the user has access to the data record of the dataset, rendering, within the host container at an anchor location, an embedded application view based on the data record of the dataset.

Abstract: A method includes receiving a natural language query specifying an action for an assistant interface to perform and selecting one or more business large language models (LLMs) for the assistant interface to interact with to fulfill performance of the action. For each business LLM, method also includes accessing an adapter module to structure the natural language query into a respective prompt specifically formulated for the corresponding business LLM, issuing, for input to the corresponding business LLM, the respective prompt, and receiving corresponding response content from the corresponding business LLM that conveys details regarding performance of a corresponding portion of the action. The method also includes presenting, for output from the user device, presentation content based on the corresponding response content received from each corresponding business LLM.

Abstract: A method for carrier network integration through a user proxy interface includes receiving a request from a mobile device associated with a subscriber of a carrier provider to establish voice services with the carrier provider for a companion device linked to the mobile device. The request includes a subscriber identifier of the mobile device. The method also includes authenticating the companion device based on the subscriber identifier, obtaining session initiation protocol (SIP) credentials corresponding to the subscriber identifier, and registering the SIP credentials for the companion device at a network interface proxy. The network interface proxy is in communication with an internet protocol multimedia subsystem (IMS) of the carrier provider and the companion device. The method also includes establishing voice services between the companion device and the IMS through the network interface proxy using the SIP credentials.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for storing and accessing data in a cloud system. One of the methods includes receiving an identification of log data that records occurrences of events; receiving a specification of a plurality of different event types to be indexed; indexing the log data according to the specification and group identifiers; receiving a query specifying a reference parameter and requesting one or more predicted events; searching the indexed groups to identify a plurality of groups having events associated with the reference parameter; computing one or more predicted events, from the identified plurality of groups, that are most likely to co-occur in the indexed groups with events associated with the reference parameter; and providing the computed one or more predicted events.

Abstract: A method for securing messages includes obtaining, at a message server, a message for a user of a message service hosted by the message server. The message includes a header and the header includes a digital signature signed by an author of the message and a list of one or more recipients of the message. The method includes determining whether the digital signature by the author is valid and determining, using the list of one or more recipients, whether the user is a declared recipient of the message. When the digital signature by the author is valid and the user is the declared recipient of the message, the method includes delivering the message to a user device of the user. When the digital signature by the author is valid and the user is not the declared recipient of the message, the method includes alerting the user.

Abstract: The technology relates to enhancing speech emotion recognition models with methods that enable the use of unlabeled data by inferring weak emotion labels. This is done by pre-trained large language models through weakly-supervised learning. For inferring weak labels constrained to a taxonomy, a textual entailment approach selects an emotion label with the highest entailment score for a speech transcript extracted via automatic speech recognition. The system may employ a method that generates, by one or more processors, a text transcript for a snippet of input speech, and then applies the text transcript to a pre-trained language model. The system can generate, using the pre-trained language model according to an engineered prompt and a predetermined taxonomy, a textual entailment from the text transcript. Based on this, the system may generate, by the one or more processors using the textual entailment, a predicted emotion corresponding to the input speech.

Abstract: Generating audio tracks is provided. The system selects a digital component object having a visual output format. The system determines to convert the digital component object into an audio output format. The system generates text for the digital component object. The system selects, based on context of the digital component object, a digital voice to render the text. The system constructs a baseline audio track of the digital component object with the text rendered by the digital voice. The system generates, based on the digital component object, non-spoken audio cues. The system combines the non-spoken audio cues with the baseline audio form of the digital component object to generate an audio track of the digital component object. The system provides the audio track of the digital component object to the computing device for output via a speaker of the computing device.

Abstract: Techniques and apparatuses are described for adaptive phase-changing device power-saving operations. In aspects, a base station determines to transition an adaptive phase-changing device (APD) into an enabled APD-PS mode and determines an APD-PS configuration for the APD that specifies a framework for operating in the enabled APD-PS mode. The base station then directs the APD to operate in the enabled APD-PS mode by communicating the APD-PS configuration to the APD and transmits or receives wireless signals using a surface of the APD and based on the APD-PS configuration.

Abstract: A method includes receiving audio data corresponding to a query spoken and processing the audio data to generate multiple candidate hypotheses each represented by a respective sequence of hypothesized terms. For each candidate hypothesis, the method includes determining whether the sequence of hypothesized terms includes a source phrase from a list of phrase correction pairs. Each phrase correction pair includes a corresponding source phrase that was misrecognized and a corresponding target phrase replacing the source phrase. When the respective sequence of hypothesized terms includes the source phrase, the method includes generating a corresponding additional candidate hypothesis that replaces the source phrase.

Abstract: The present disclosure provides a closed loop, self-learning system that automatically optimizes what experiences should be presented to each customer. Instead of relying on rules and external targeting, it observes customer reactions to continuously improve performance and adapt to environment changes.

Abstract: Techniques and apparatuses are described for multiple-input multiple-output transmissions using adaptive phase-changing devices. In aspects, a base station selects one or more adaptive phase-changing devices, APDs, to use in at least one communication path for multiple-input, multiple-output, MIMO, transmissions. The base station can perform a channel characterization process for the at least one communication path using the at least one APD and at least one UE. Based on results of the channel characterization process, the base station configures the at least one APD by which to implement single user-MIMO communication with a UE or multiple user-MIMO communication with multiple UEs. By so doing, the base station may implement MIMO transmissions using APDs to communicate with the at least one UE using same time and frequency resources, which can improve spectral efficiency of a wireless network.

Abstract: A method for identifying malicious software includes receiving and executing a software application, identifying a plurality of uniform resource identifiers the software application interacts with during execution of the software application, and generating a vector representation for the software application using a feed-forward neural network configured to receive the plurality of uniform resource identifiers as feature inputs. The method also includes determining similarity scores for a pool of training applications, each similarity score associated with a corresponding training application and indicating a level of similarity between the vector representation for the software application and a respective vector representation for the corresponding training application.

Abstract: A method for sharing read access to a document stored on memory hardware. The method includes receiving a shared read access command from a sharor sharing read access to a sharee for a document stored on memory hardware in communication with the data processing hardware, and receiving a shared read access request from the sharee. The shared read access command includes an encrypted value and a first cryptographic share value based on a write key, a read key, a document identifier, and a sharee identifier. The method also includes multiplying the first and second cryptographic share values to determine a cryptographic read access value. The cryptographic read access value authorizes read access to the sharee for the document. The method also includes storing a read access token for the sharee including the cryptographic read access value and the encrypted value in a user read set of the memory hardware.

Abstract: A method for handling contradictory queries on a shared device includes receiving a first query issued by a first user, the first query specifying a first long-standing operation for a digital assistant to perform, and while the digital assistant is performing the first long-standing operation, receiving a second query, the second query specifying a second long-standing operation for the digital assistant to perform. The method also includes determining that the second query was issued by another user different than the first user and determining, using a query resolver, that performing the second long-standing operation would conflict with the first long-standing operation. The method further includes identifying one or more compromise operations for the digital assistant to perform, and instructing the digital assistant to perform a selected compromise operation among the identified one or more compromise operations.

Abstract: This disclosure describes a method to calibrate a position of an optical image stabilization (OIS) lensing element 308 based on an electric current reading of one or more areas of a mobile imaging device 200. The position is a deviation from a center position, where the OIS lensing element 308 is not influenced by a force. A coupling compensation coefficient is generated based on the electric current reading. A derived value for the position is adjusted based on the coupling compensation coefficient. A scaling sensitivity coefficient is generated based on the electric current reading. The derived value for the position is further adjusted based on the scaling sensitivity coefficient. The coupling compensation coefficient and the scaling sensitivity coefficient are further based on maximum and minimum values for the Hall Effect sensor at the temperature reading and a calibration temperature.

Abstract: A method, device, and computer-readable storage medium for predicting pronunciation of a text sample. The method includes selecting a predicted text sample corresponding to an audio sample, receiving a correction text sample corresponding to the audio sample, updating an encoding of allowable pronunciations of the correction text sample based on the predicted text sample and the audio sample, the updated encoding of allowable pronunciations of the correction text sample including a pronunciation of the predicted text sample, and predicting a pronunciation of the correction text sample based on the updated encoding of allowable pronunciations of the correction text sample.

Abstract: This document describes systems and techniques directed at zonal attenuation compensation. In aspects, a system includes a graphics processing unit configured to provide image data to a display panel. A zonal attenuation module is configured to combine a zonal attenuation mask with the image data to generate masked image data, the masked image data having a reduced brightness for portions of data corresponding to one or more regions on the display panel based on the zonal attenuation mask. An inverse zonal attenuation module is configured to apply an inverse zonal attenuation mask to the masked image data to reduce a brightness for additional portions of data corresponding to one or more additional regions on the display panel effective to offset increased brightness in the one or more additional regions on the display panel.

Abstract: A method including receiving, from a developer device, a request to build an execution environment for a software application, the software application comprising a manifest of dependencies. The method also includes generating, using a bootstrap execution environment based on the manifest of dependencies, the execution environment for the software application comprising a set of application dependencies, and storing the execution environment at a data store. The method further includes executing the software application in the execution environment.

Abstract: Permission control and management for messaging application bots is described. A method can include providing a messaging application, on a first computing device associated with a first user, to enable communication between the first user and another user, and detecting, at the messaging application, a user request. The method can also include programmatically determining that an action in response to the user request requires access to data associated with the first user, and causing a permission interface to be rendered in the messaging application, the permission interface enabling the first user to approve or prohibit access to the data associated with the first user. The method can include accessing the data associated with the first user and performing the action in response to the user request, upon receiving user input from the first user indicating approval of the access to the data associated with the first user.

Abstract: A method includes obtaining a pre-trained machine learning model and a training embedding snapshot from a remote system, and obtaining one or more input data samples captured by a user device. The method includes, for each particular input data sample of the one or more input data samples, processing, using an on-device machine learning model corresponding to the pre-trained machine learning model, the particular input data sample to generate a corresponding on-device embedding and one or more corresponding predicted outputs, and generating, using the training embedding snapshot and the corresponding on-device embedding, corresponding performance data. The method includes aggregating the corresponding performance data for the one or more input data samples to determine one or more performance metrics for the on-device machine learning model, and transmitting the one or more performance metrics to the remote system.

Abstract: A method includes processing, using a speech recognizer, a first portion of audio data to generate a first lattice, and generating a first partial transcription for an utterance based on the first lattice. The method includes processing, using the recognizer, a second portion of the data to generate, based on the first lattice, a second lattice representing a plurality of partial speech recognition hypotheses for the utterance and a plurality of corresponding speech recognition scores. For each particular partial speech recognition hypothesis, the method includes generating a corresponding re-ranked score based on the corresponding speech recognition score and whether the particular partial speech recognition hypothesis shares a prefix with the first partial transcription.

Abstract: This document describes techniques and devices for blood-solute calculation with a mobile device using non-invasive spectroscopy. A mobile device includes a light source that emits light toward an interferometer that uses mirrors to separate and recombine the light. The interferometer directs the recombined light toward a person. Light reflected from, or transmitted through, the person is received through a reception port to a photodetector that outputs photodetector data that corresponds to a measured light intensity of the reflected and transmitted light as a function of a path length of the light or a mirror position of the interferometer. Based on the photodetector data, an interferogram is generated. Applying a technique such as a Fourier transform to the interferogram, a spectrum data set of the reflected and transmitted light is generated. Based on the spectrum data set, a concentration of solutes in the person's blood is calculated.

Abstract: A method includes determining a cluster reliability of a computing cluster including a maximum computing capacity and representative of a reliability of the computing cluster when utilizing an entirety of the maximum computing capacity. The operations include receiving a provisioning request of the computing cluster including a threshold reliability of the computing cluster. In response to the provisioning request, determining, using the cluster reliability, a reserved computing capacity of the computing cluster based on the threshold reliability. The reserved computing capacity is less than the maximum computing capacity. Based on the reserved computing capacity and the maximum computing capacity, the operations include determining an unreserved computing capacity of the computing cluster. The operations include provisioning the computing cluster for execution of a user workload. The user workload executes on the unreserved computing capacity.

Abstract: This document discloses techniques, apparatuses, and systems for efficient and secure data handling using domain-oriented masking. In aspects, efficient and secure data handling using domain-oriented masking enables circuit resources (e.g., flip flops, data) to be shared between portions of an integrated circuit (IC). Specifically, an input register of a Galois-Field (GF) multiplier and a pipeline register within a stage of an Advanced Encryption Standard Substitution-Box (S-Box) may be implemented as sharing a single flip flop. Some ICs may utilize multiple S-Boxes, including multiple GF multipliers that are provided randomness each time the input is updated. In this case, an output from a previous stage of a first S-box may be provided as randomness to a subsequent stage of a second S-Box to limit the need for entropy generation circuitry. In this way, efficient and secure data handling using domain-oriented masking may decrease circuit cost and circuit area without impacting security.

Abstract: A method for in process asynchronous out of memory logs for remote containerized deployments includes executing a container process within a container. The method further includes, writing, by the container process, a log of the container process to a first log file. The method also includes storing, by the container process, the first log file at non-volatile memory mounted to the container. The method includes determining, by the container process, that the first log file satisfies a threshold size. In response to determining that the first log file satisfies the threshold size, the method includes writing the log of the container process to a second log file, compressing the first log file into a first compressed log file, and transmitting the first compressed log file to a remote endpoint.

Abstract: Various arrangements of antenna systems are detailed herein. Such an antenna system can include first antenna connected to a printed circuit board. The antenna system further includes a second antenna connected to the printed circuit board. The antenna system further includes a decoupling structure connected to the printed circuit board at a location between the first antenna and the second antenna.

Abstract: A method includes receiving a reference audio signal corresponding to reference speech spoken by a target speaker with atypical speech, and generating, by a speaker embedding network configured to receive the reference audio signal as input, a speaker embedding for the target speaker. The speaker embedding conveys speaker characteristics of the target speaker. The method also includes receiving a speech conversion request that includes input audio data corresponding to an utterance spoken by the target speaker associated with the atypical speech. The method also includes biasing, using the speaker embedding generated for the target speaker by the speaker embedding network, a speech conversion model to convert the input audio data corresponding to the utterance spoken by the target speaker associated with atypical speech into an output canonical representation of the utterance spoken by the target speaker.

Abstract: A method for on demand serverless container based storage transfer includes receiving a request to transfer data from a first device to a second device, the first device hosted at a private cloud, the private cloud isolated from the Internet. The method includes determining that the first device is communicatively connected to the private cloud. The method also includes, in response to determining that the first device is communicatively connected to the private cloud, instantiating a container at the first device, the container configured to receive the data from the first device without directly accessing a local storage of the first device. The method includes transferring, using the container, the data from the first device to the second device.

Abstract: A method for providing elastic columnar cache includes receiving cache configuration information indicating a maximum size and an incremental size for a cache associated with a user. The cache is configured to store a portion of a table in a row-major format. The method includes caching, in a column-major format, a subset of the plurality of columns of the table in the cache and receiving a plurality of data requests requesting access to the table and associated with a corresponding access pattern requiring access to one or more of the columns. While executing one or more workloads, the method includes, for each column of the table, determining an access frequency indicating a number of times the corresponding column is accessed over a predetermined time period and dynamically adjusting the subset of columns based on the access patterns, the maximum size, and the incremental size.

Abstract: A method for a virtual network of a mobile device includes, for the mobile device executing a user application and simultaneously connected to a first wireless network and a second wireless network, selecting a remote server from a plurality of remote servers. The method also includes establishing the virtual network between the mobile device and the selected remote server. The virtual network includes at least one tunnel between the mobile device and the selected remote server over the first wireless network and the second wireless network. The method also includes transmitting data from the user application to the selected remote server over the virtual network. The data, when received by the selected remote server, causes the selected remote server to route the data to a destination server.

Abstract: This document describes systems and techniques for determining whether an earbud is removed from within an ear of a user. The systems and techniques employ an earbud including a housing having a distal end and a proximal end. The distal end includes a magnetically-sensitive section, the distal end of the housing being configured to be magnetically attracted to a charging receptacle and insertable within an ear of a user. On-head detection (OHD) logic is electrically coupled to the magnetically-sensitive section at the distal end, the OHD logic configured to determine based on a distal-end capacitance measured using the magnetically-sensitive section whether the distal end of the housing is within the ear of the user.

Abstract: A method includes assigning a plurality of workloads to an isolated secure compute environment on a distributed computing system based on respective security criteria for each of the plurality of workloads, the isolated secure compute environment isolated from one or more other isolated secure compute environments on the distributed computing system. While executing the plurality of workloads in the isolated secure compute environment on the distributed computing system, the method also includes determining resource utilization for the isolated secure compute environment, and adjusting, using the determined resource utilization, a number of computing resources assigned to the isolated secure compute environment.