Abstract: Storage devices include a memory array which stores host data received from a host computing device. During normal operations, the storage device may encounter a fatal error which can halt functionality. To restore functionality without system disconnection or third-party interventions, the storage device can store recovery data within a host memory buffer prior to encountering a fatal error. The recovery data can be replay protected memory data and/or firmware recovery data that can be written to the host memory buffer upon power on or during a firmware update. When a fatal error occurs, the recovery data can be accessed to try and rebuild file and mapping systems to restore full operation of the storage device. When full operational restoration is not possible, host data can at least be copied from the storage device prior to utilizing firmware recovery data to restore the storage device to an erased but functional state.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform a corresponding action, such as streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user. The speech recognition platform, in combination with the device, may therefore facilitate efficient interactions between the user and a voice-controlled device.

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: Synchronized output of audio on a group of devices can comprise sending audio data from an audio distribution master device to one or more slave devices in the group. Scores can be assigned to respective audio playback devices, the scores being indicative of a performance level of the respective audio playback devices acting as a master device. The device with the highest score is designated as a candidate master device and one or more remaining devices are designated as a candidate slave(s). A throughput test is conducted with the highest scoring device acting as the candidate master device. The results of the throughput test are used to determine a master device for a group of devices. Latency of the throughput test can be reduced by using a prescribed time period for completion of the throughput test, and/or by selecting a first group configuration to passes the throughput test.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input from a device. The NLP system may also receive one or more signals representing one or more assistants to be implemented with respect to the natural language input. The NLP system may intelligently select an assistant to be invoked with respect to the natural language input. Once the assistant is selected, the NLP system may cause content, output to a user, to have characteristics specific to the assistant.

Abstract: Techniques for detecting spam accounts in a system are described. The system may analyze speech characteristics of communication content (e.g., telephone call content, VoIP content, audio messaging, etc.) to determine whether multiple devices or user profiles are associated with overlapping communications. The system may also analyze text transcriptions of communication content to determine whether multiple devices or user profiles are associated with overlapping communications. If so, the system may mitigate, such as throttling service, disabling accounts, and the like.

Abstract: Synchronized output of audio on a group of devices can comprise sending audio data from an audio distribution master device to one or more slave devices in the group. Scores can be assigned to respective audio playback devices, the scores being indicative of a performance level of the respective audio playback devices acting as a master device. The device with the highest score is designated as a candidate master device and one or more remaining devices are designated as a candidate slave(s). A throughput test is conducted with the highest scoring device acting as the candidate master device. The results of the throughput test are used to determine a master device for a group of devices. Latency of the throughput test can be reduced by using a prescribed time period for completion of the throughput test, and/or by selecting a first group configuration to passes the throughput test.

Abstract: Described herein is a system for enabling a user to multitask by allowing a user to pause or interrupt an on-going interaction with a skill. The system monitors a state of a skill session, and updates the state to allow the user or system to suspend the session. The user may provide an instruction to pause an active session, causing the system to place the session in a suspended state. The user may then provide an instruction to resume the suspended session, causing the system to place the session in an active state. In other cases, the user input may be a request during an active session that requires invoking another skill. The system may place the current session in a suspended state, and invoke a second skill session to monitor the interaction with a second skill. When the interaction with the second skill is completed, the system may resume the previous session by placing it in an active state.

Abstract: An organic polymer comprising an organic polymer fragment and at least one S-alkylsilyl hydrocarbonthioate group or at least one S-alkylstannyl hydrocarbonthioate group bonded to the backbone of the organic polymer fragment through a C—Si covalent bond and their methods or production are provided. The organic polymer backbone can be derived from the anionic polymerization of monomers containing C—C unsaturation. The silicon or tin atom can be further bonded to two alkoxy groups, two hydrocarbon groups or to one alkoxy group and one hydrocarbon group.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: A system that determines that devices are co-located in an acoustic region and selects a single device to which to send incoming notifications for the acoustic region. The system may group devices into separate acoustic regions based on selection data that selects between similar audio data received from multiple devices. The system may select the best device for each acoustic region based on a frequency that the device was selected previously, input/output capabilities of the device, a proximity to a user, or the like. The system may send a notification to a single device in each of the acoustic regions so that a user receives a single notification instead of multiple unsynchronized notifications. The system may also determine that acoustic regions are associated with different locations and select acoustic regions to which to send a notification based on location.

Abstract: Systems and methods for precomputed communication parameters are disclosed. A request to establish a communication channel may be received from a first device at a remote system. The remote system may query precached communication parameters associated with the first device to identify modalities and/or codecs associated with the first device. The remote system may also identify the second device to establish the communication channel with and may identify modalities and/or codecs associated with the second device, such as by utilizing user accounts associated with the devices. A transport-address type may be identified, such as based on whether the devices are associated with the same network access point identifier and/or based on past communication channels established between the devices.

Abstract: This disclosure describes, in part, context-driven device arbitration techniques to select a speech interface device from multiple speech interface devices to provide a response to a command included in a speech utterance of a user. In some examples, the context-driven arbitration techniques may include executing multiple pipeline instances to analyze audio signals and device metadata received from each of the multiple speech interface devices which detected the speech utterance. A remote speech processing service may execute the multiple pipeline instances and analyze the audio signals and/or metadata, at various stages of the pipeline instances, to determine which speech interface device is to respond to the speech utterance.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: A system that determines that devices are co-located in an acoustic region and selects a single device to which to send incoming notifications for the acoustic region. The system may group devices into separate acoustic regions based on selection data that selects between similar audio data received from multiple devices. The system may select the best device for each acoustic region based on a frequency that the device was selected previously, input/output capabilities of the device, a proximity to a user, or the like. The system may send a notification to a single device in each of the acoustic regions so that a user receives a single notification instead of multiple unsynchronized notifications. The system may also determine that acoustic regions are associated with different locations and select acoustic regions to which to send a notification based on location.

Abstract: Techniques for using validated communications identifiers of a user's communications profile to resolve entries in another user's contact list are described. When a user imports a contact list, the contact list may include multiple entities related to the same person. The system may identify one of the entries in the contact list that corresponds to a validated communications identifier stored in another user's communications profile. The system may identify other validated communications identifiers in the other user's communications profile and cross-reference them against the entries of the contact list. If the system determines the contact list includes entries for the different validated communications identifiers of the other user, the system may consolidate the entries into a single entry associated with the other user.

Abstract: Synchronized output of audio on a group of devices can comprise sending audio data from an audio distribution master device to one or more slave devices in the group. Scores can be assigned to respective audio playback devices, the scores being indicative of a performance level of the respective audio playback devices acting as a master device. The device with the highest score is designated as a candidate master device and one or more remaining devices are designated as a candidate slave(s). A throughput test is conducted with the highest scoring device acting as the candidate master device. The results of the throughput test are used to determine a master device for a group of devices. Latency of the throughput test can be reduced by using a prescribed time period for completion of the throughput test, and/or by selecting a first group configuration to passes the throughput test.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant during a dialog between one or more users and the NLP system are described. The NLP system may receive a first natural language input and associate same with a dialog identifier. The NLP system may output audio, responsive to the first natural language input, in a first NLP system assistant's voice. Thereafter, the NLP system may receive a second natural language input and associate same with the dialog identifier. The NLP system may output audio, responsive to the second natural language input, in a second NLP system assistant's voice.