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

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a packet from a client, the packet having header information including a destination Internet Protocol (IP) address, a destination port, a source IP address, and a source port, and wherein the source IP address and source port are associated with the client; selecting a destination virtual machine based on the destination port; modifying the packet by replacing the destination IP address in the header information with an IP address of the selected destination virtual machine; and sending the modified packet to the destination virtual machine.

Abstract: The various implementations described herein include methods and systems for synchronous audio playback. An electronic device can receive an identification of a first device as a common clock device that has a first internal clock being designated as a master clock. The electronic device receives a synchronized audio playback command that includes audio data to be output and a future playback time. In response to receiving the audio data, the device determines a synchronized audio playback time for audio to be output. An optimal time for output can be calculated and transmitted to the server system for future playback time calculations.

Abstract: A method includes receiving a training dataset that includes one or more spoken training utterances for training an automatic speech recognition (ASR) model. Each spoken training utterance in the training dataset paired with a corresponding transcription and a corresponding target sequence of auxiliary tokens. For each spoken training utterance, the method includes generating a speech recognition hypothesis for a corresponding spoken training utterance, determining a speech recognition loss based on the speech recognition hypothesis and the corresponding transcription, generating a predicted auxiliary token for the corresponding spoken training utterance, and determining an auxiliary task loss based on the predicted auxiliary token and the corresponding target sequence of auxiliary tokens. The method also includes the ASR model jointly on the speech recognition loss and the auxiliary task loss determined for each spoken training utterance.

Abstract: In aspects, a base station establishes a wireless connection with a user equipment, UE. The base station determines to include at least a first adaptive phase-changing device, APD, and a second APD in a wireless communication path with the UE. In response to determining to include multiple APDs in the communication path, the base station determines a first surface configuration for a first surface of the first APD and a second surface configuration for a second surface of the second APD. The base station directs the first APD to apply the first surface configuration to the first surface and directs the second APD to apply the second surface configuration to the second surface. The base station and the UE communicate with the UE using wireless transmissions that travel along a wireless communication path that includes the first surface of the first APD and the second surface of the second APD.

Abstract: An indexed sequence of bits in a buffer is allocated for tracking a battery charging state. The indexed sequence of bits has a first number of bits. A battery voltage of a rechargeable battery is sampled at a sampling rate. For each sampled battery voltage, the battery voltage is compared with a voltage threshold. A next bit position in the indexed sequence of bits is identified. In accordance with a determination that a comparison result is true, a predefined first value is added to the next bit position. A second number of bits that are filled with the predefined first value is determined. A ratio between the second number and the first number is also determined. In accordance with a determination that the ratio exceeds a threshold step-down ratio, a battery charge voltage is stepped down. The rechargeable battery is charged to a step-down voltage.

Abstract: The present disclosure describes thermal mitigation for an electronic speaker device and associated systems and methods. The thermal mitigation includes monitoring several thermal zones to determine or estimate thermal conditions in corresponding parts of the electronic speaker device. The thermal zones may include a System-on-Chip (SoC) integrated circuit (IC) component, audio components including power-dissipating IC components, and a temperature of an exterior surface of a housing component of the electronic speaker device. To mitigate thermal runaway, different throttling schemes may be triggered based on the thermal zones exceeding certain thermal limits. The throttling schemes may include reducing the amount of power supplied to the SoC, reducing audio power of the audio components to a lower wattage, or manipulating SoC cores such as by disabling one or more of the cores or adjusting utilization of the SoC cores.

Abstract: A method for extracting entities comprises obtaining a document that includes a series of textual fields that includes a plurality of entities. Each entity represents information associated with a predefined category. The method includes generating, using the document, a series of tokens representing the series of textual fields. The method includes generating an entity prompt that includes the series of tokens and one of the plurality of entities and generating a schema prompt that includes a schema associated with the document. The method includes generating a model query that includes the entity prompt and the schema prompt and determining, using an entity extraction model and the model query, a location of the one of the plurality of entities among the series of tokens. The method includes extracting, from the document, the one of the plurality of entities using the location of the one of the plurality of entities.

Abstract: A method includes a hierarchical dataset that includes a root-data object and data collections nested under the root-data object. Each data collection includes one or more data objects, each data object associated with one or more other data collections. The method also includes displaying a hierarchical user interface on a screen. The hierarchical user interface includes column. The columns include data-object columns and data-collection columns, wherein the columns alternate between data-object columns and data-collection columns. Each data-object column displays a list of the one or more data objects of a respective data collection. Each data-collection column displays a list of the one or more data collections of a respective data object, the data-collection columns includes a root-data-collection column displaying a list of the one or more data collections associated with the root-data object.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving audio data that corresponds to an utterance. The actions further include determining that the utterance likely includes a particular, predefined hotword. The actions further include transmitting (i) data indicating that the computing device likely received the particular, predefined hotword, (ii) data identifying the computing device, and (iii) data identifying a group of nearby computing devices that includes the computing device. The actions further include receiving an instruction to commence speech recognition processing on the audio data. The actions further include in response to receiving the instruction to commence speech recognition processing on the audio data, processing at least a portion of the audio data using an automated speech recognizer on the computing device.

Abstract: Various arrangements are presented for increasing a link margin of a wireless audio link. A short-range wireless communication link having a first physical layer (PHY) symbol rate is established between an audio source device and an audio output device. An audio stream is transmitted using the communication link, which includes a connected isochronous stream (CIS) link. A number of packet retransmissions are detected on the CIS. Based on the detected number of packet retransmissions on the CIS, the first PHY symbol rate of the CIS can be altered to a second PHY symbol rate for transmitting the audio stream.

Abstract: A method includes receiving context biasing data that includes a set of unspoken textual utterances corresponding to a particular context. The method also includes obtaining a list of carrier phrases associated with the particular context. For each respective unspoken textual utterance, the method includes generating a corresponding training data pair that includes the respective unspoken textual utterance and a carrier phrase. For each respective training data pair, the method includes tokenizing the respective training data pair into a sequence of sub-word units, generating a first higher order textual feature representation for a corresponding sub-word unit, receiving the first higher order textual feature representation, and generating a first probability distribution over possible text units. The method also includes training a speech recognition model based on the first probability distribution over possible text units.

Abstract: This document describes techniques and apparatuses that enable determining expected hash-values in functions with control flow. A computing device receives a function comprising function instructions within at least three basic blocks connected via multiple execution paths. Hash-input instructions are inserted within a plurality of the basic blocks that indirectly force hash values at the respective insertion points. Hash values at ends of the plurality of the basic blocks are set to a canonical value and an expected hash-value and hash input-values are calculated using a hash function. By using the canonical value and the hash input-values, the expected hash-value is the same regardless of which execution path is executed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a machine learning model that is trained to perform a machine learning task. In one aspect, a method comprises receiving a request to train a machine learning model on a set of training examples; determining a set of one or more meta-data values characterizing the set of training examples; using a mapping function to map the set of meta-data values characterizing the set of training examples to data identifying a particular machine learning model architecture; selecting, using the particular machine learning model architecture, a final machine learning model architecture for performing the machine learning task; and training a machine learning model having the final machine learning model architecture on the set of training examples.

Abstract: Identity systems, methods, and media for auditing and notifying users concerning verifiable claims are provided.

Abstract: Generating a prediction block for coding a block includes determining an adaptive intra-prediction mode indicative of at least a training region and a configuration of neighboring pixel locations. The training region neighbors the block and includes a plurality of reconstructed pixels. Filter coefficients are obtained. The filter coefficients are used to obtain respective prediction pixels of neighboring pixels within the training region when applied to defined respective configurations of the neighboring pixels according to the configuration of the neighboring pixels. The filter coefficients minimize a function of differences, each difference being a respective difference between a pixel in the training region and a prediction of that pixel in the training region.

Abstract: In some implementations, an utterance that requests a voice call is received, the utterance is classified as spoken by a particular known user, the particular known user is determined to be associated with a personal voice number, and in response to determining that the particular known user is associated with a personal voice number, the voice call is initiated with the personal voice number.

Abstract: An automated cargo delivery system is provided, including an automated guided vehicle having a housing defining a recess therein and a propulsion system configured to move the housing. The recess may be configured to receive a plurality of swappable carriers each having a uniform width in a horizontal direction and a uniform height in a vertical direction perpendicular to the horizontal direction. Each of the swappable carriers may be configured to be engaged within the recess. The plurality of swappable carriers may include a first swappable carrier and a second swappable carrier. A method of delivering cargo with the automated guided vehicle is also provided. The method may include alternatingly inserting and engaging the first swappable carrier and the second swappable carrier into the recess of the automated guided vehicle.

Abstract: The present disclosure provides systems and methods for adjusting the playback speed of accessories based on the buffer level of the received content. The accessories may receive content from a host device at a certain speed. The incoming speed of the content may be different than the playback speed of the content. Therefore, a buffer level of the received content may be determined using a linear least square (“LLS”) fit of the buffer level, the average of the buffer level, or a phased locked loop (“PLL”) approach. Based on a difference between the buffer level and the playback speed, a speed adjustment may be determined. Instructions may be transmitted from a primary accessory to a secondary accessory to adjust the playback speed by a certain amount at a certain time. This may ensure that the accessories remain in sync. The accessories may then adjust their respective playback speeds.