Abstract: The present invention is directed to a differential privacy platform in which the privacy risk of a computation can be objectively and quantitatively calculated. This measurement is performed by simulating a sophisticated privacy attack on the system for various measures of privacy cost or epsilon, and measuring the level of success of the attack. In certain embodiments, a linear program reconstruction-type attack is used. By calculating the loss of privacy resulting from sufficient attacks at a particular epsilon, the platform may calculate a level of risk for a particular use of data. The privacy budget for the use of the data may thereby be set and controlled by the platform to remain below a desired risk threshold.

Abstract: A data analytics platform provides secure access to federated data for advanced analytics and machine learning. No raw data is exposed or moved outside its original location, thereby providing data privacy. A coordinator located in the provider cloud communicates with runners in each client data silo. The runners ensure that no raw private data is ever exposed to the coordinator. Silo managers are implemented in the client data silo in order to manage and maintain the client cloud components of the platform remotely. In some embodiments, the platform can anonymize verified models for privacy and compliance, and users can export and deploy secure models outside the original data location.

Abstract: A speech interface device is configured to defer encryption of audio data on-device until a time when the encryption operation is not competing with other computationally-intensive operations for responding to the audio data. For example, audio data based on sound captured in an environment of the speech interface device can be stored in volatile memory of the speech interface device, without encrypting it, until a set of processing operations (e.g., ASR processing, NLU processing, audio event processing, etc.) performed based on the audio data have stopped. Based on a determination that these processing operations for responding to the audio data have stopped, the logic may encrypt the audio data to generate encrypted data, and the encrypted data can be stored in non-volatile memory of the speech interface device for uploading to a remote system when a connection is available.

Abstract: This disclosure proposes systems and methods enabling on-device/hybrid processing of speech requests using a hub device. The hub device is capable of receiving audio data from surrounding devices and performing speech processing on the audio data to improve latency and/or provide functionality to other devices within a private network. The hub device may receive multiple requests corresponding to different utterances. If the hub device receives a second utterance while processing a first utterance, the hub device may send an error notification, process the first utterance and the second utterance sequentially, suspend processing of the first utterance to process the second utterance first, send the second utterance to another hub device or remote system, or suspend processing of the first utterance and send the first utterance to the remote system in order to process the second utterance.

Abstract: This disclosure proposes systems and methods enabling on-device/hybrid processing of speech requests using a hub device. The hub device is capable of receiving audio data from surrounding devices and performing speech processing on the audio data to improve latency and/or provide functionality to other devices within a private network. The hub device may receive multiple requests corresponding to different utterances. If the hub device receives a second utterance while processing a first utterance, the hub device may send an error notification, process the first utterance and the second utterance sequentially, suspend processing of the first utterance to process the second utterance first, send the second utterance to another hub device or remote system, or suspend processing of the first utterance and send the first utterance to the remote system in order to process the second utterance.

Abstract: A speech interface device is configured to switch between languages, at the request of a user, in order to locally process utterances spoken in different languages, even in instances when a remote system is unavailable to, slower than, or otherwise less preferred than the speech interface device. For example, a user can request to set the language setting of the speech interface device to a second language, different from a first language to which the language setting of the device is currently set. Based on this user request, a local speech processing component of the device may load a language model(s) associated with the second language. The speech interface can also output voice prompts in the second language to manage the user's experience while a language update is in progress on the speech interface device.

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: A speech interface device is configured to defer encryption of audio data on-device until a time when the encryption operation is not competing with other computationally-intensive operations for responding to the audio data. For example, audio data based on sound captured in an environment of the speech interface device can be stored in volatile memory of the speech interface device, without encrypting it, until a set of processing operations (e.g., ASR processing, NLU processing, audio event processing, etc.) performed based on the audio data have stopped. Based on a determination that these processing operations for responding to the audio data have stopped, the logic may encrypt the audio data to generate encrypted data, and the encrypted data can be stored in non-volatile memory of the speech interface device for uploading to a remote system when a connection is available.

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: 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.