Abstract: Described herein are systems, methods, and computer readable media for dynamically determining a language variant to use for vehicle output to a vehicle occupant based on the vehicle's location. A geographic region may include multiple sub-regions, each of which may be associated with a respective one or more language variants. As an example, a geographic region may be a state or province, and each sub-region may have one or more dialects that are spoken by individuals in that sub-region. In some cases, a particular dialect may be predominant in a given sub-region. As a vehicle traverses a travel path, it may determine its current location, which geographic sub-region includes that location, and which language variant (e.g., dialect) is predominant there. That language variant may then be selected for in-vehicle communication with a vehicle occupant. The vehicle location determination may be made at or near where the occupant entered the vehicle.

Abstract: In general, the subject matter described in this specification can be embodied in methods, systems, and program products for receiving s voice query at a mobile computing device and generating data that represents content of the voice query. The data is provided to a server system. A textual query that has been determined by a speech recognizer at the server system to be a textual form of at least part of the data is received at the mobile computing device. The textual query is determined to include a carrier phrase of one or more words that is reserved by a first third-party application program installed on the computing device. The first third-party application is selected, from a group of one or more third-party applications, to receive all or a part of the textual query. All or a part of the textual query is provided to the selected first application program.

Abstract: A method performed by an encoder. The method comprises determining envelope representation residual coefficients as first compressed envelope representation coefficients subtracted from the input envelope representation coefficients. The method comprises transforming the envelope representation residual coefficients into a warped domain so as to obtain transformed envelope representation residual coefficients. The method comprises applying, at least one of a plurality of gain-shape coding schemes on the transformed envelope representation residual coefficients in order to achieve gain-shape coded envelope representation residual coefficients, where the plurality of gain-shape coding schemes have mutually different trade-offs in one or more of gain resolution and shape resolution for one or more of the transformed envelope representation residual coefficients.

Abstract: A dialog device according to an embodiment includes an acquisition unit configured to acquire a user utterance input by a user, a plurality of generation units configured to generate a system utterance corresponding to the user utterance, and an output unit configured to output the system utterance generated by one generation unit selected from the plurality of generation units. The plurality of generation units include a first generation unit having a first scenario and a second generation unit having a second scenario different from the first scenario. The output unit outputs a first system utterance generated by the first generation unit in response to the user utterance, in a first expression format, and outputs a second system utterance generated by the second generation unit in response to the user utterance, in a second expression format different from the first expression format, following the first system utterance.

Abstract: A device initiates voice control through gaze detection. The device detects that a user is gazing at a gaze target. Responsive to that detection, the device captures audio and performs automatic speech recognition of the captured audio to turn the audio into text. The device performs natural language understanding on the text to determine an application-specific command. The device performs application-specific processing for the application-specific command.

Abstract: Technology is provided for conversation analysis. The technology includes, receiving multiple utterance representations, where each utterance representation represents a portion of a conversation performed by at least two users, and each utterance representation is associated with video data, acoustic data, and text data. The technology further includes generating a first utterance output by applying video data, acoustic data, and text data of the first utterance representation to a respective video processing part of the machine learning system to generate video, text, and acoustic-based outputs. A second utterance output is further generated for a second user. Conversation analysis indicators are generated by applying, to a sequential machine learning system the combined speaker features and a previous state of the sequential machine learning system.

Abstract: A system for performing magnetic resonance tomography is disclosed. A control system creates a speech data stream from an acquired linguistic expression and generates a command library, which contains a selection of speech commands, to each of which one or more linguistic expressions are assigned. The selection of speech commands is loaded from a command database depending on a current system status of a magnetic resonance (MR) scanner. The control system applies a speech recognition algorithm to the speech data stream to determine whether a linguistic expression contained in the command library can be assigned to the speech data stream. If so, the acquired linguistic expression is recognized, a speech command from the command library assigned to the recognized linguistic expression is established, and a control command for controlling the MR scanner in accordance with the speech command is created.

Abstract: Methods and systems for processing of voice input to identify intents and mapped standard terminologies are provided. Using natural language processing, an intent of a voice input is identified. The intent is utilized to identify a standard terminology that maps to the intent. The standard terminology is utilized to identify information relevant to the standard terminology in a patient's electronic health record.

Abstract: The disclosed exemplary embodiments include computer-implemented systems, devices, apparatuses, and processes that maintain data confidentiality in communications involving voice-enabled devices operating within a distributed computing environment. By way of example, an apparatus may receive, from a communications system across a public communications network, a request for an element of data generated by the computing system based on first audio content obtained at a device. The apparatus may obtain the requested data element and further, may generate acoustic data representative of at least a portion of the requested data element. The apparatus may also generate an encrypted response to the received request that includes the acoustic data, and transmit the encrypted response to the device across the public communications network.

Abstract: Provided is a voice assistance system with proactive routines that couples a remote server and respective user voice interactive devices to deliver a complete experience to the end user of the device. The voice assistance system can also provide a platform to connect remote users to customize commands (e.g., proactive or reactive) to improve day-to-day operation across groups of devices and/or users. For example, routines can be built for an organization and made available to voice interactive devices distributed by or on behalf of the organization. Administrators can select features for the device and pre-configure voice assistance devices with groups of pre-selected routines to deliver a device that is ready to go out of the box. Updates to a device or routines can be based on such groups. Additionally, primary routine instances can be linked to groups where changes to the primary instance are propagated to any linked users.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for integrating speech-to-text transcription in a productivity application are presented. A request to access a real-time speech-to-text transcription of an audio signal that is being received by a second device is sent by a first device. The real-time speech-to-text transcription may be surfaced in a transcription pane of a productivity application on the first device. A request to translate the transcription to a different language may be received. The transcription may be translated in real-time and surfaced in the transcription pane. A selection of a word in the surfaced transcription may be received. A request to drag the word from the transcription pane and drop it in a window in the productivity application outside of the transcription pane may be received. The word may be surfaced in the window in the productivity application outside of the transcription pane.

Abstract: A computer-implemented conversational agent engages in a natural language conversation with a user, interpreting the natural language conversation by parsing and tokenizing utterances in the natural language conversation. Based on interpreting, a set of utterances in the natural language conversation to be recorded as a macro is determined. The macro is stored in a database with an associated macro identifier. Replaying of the macro executes a function specified in the set of utterances.

Abstract: Methods, computer program products, and systems are presented. The method, computer program products, and systems can include for instance: obtaining sensor output data from a user, wherein the sensor output data from the user includes voice data of the user; generating, during an interactive voice response session, vocal response data for presentment by a virtual agent to the user in response to the voice data, wherein the generating includes performing data access queries on one or more storage system; and prioritizing certain asset data of the one or more storage system, wherein the prioritizing is performed in dependence on data of the sensor output data.

Abstract: In some examples, a software agent executing on a server receives a communication comprising a first utterance from a customer and predicts, using an intent classifier, a first intent of the first utterance. Based on determining that the first intent is order-related, the software agent predicts, using a dish classifier, a cart delta vector based at least in part on the first utterance and modifies a cart associated with the customer based on the cart delta vector. The software agent predicts, using a dialog model, a first dialog response based at least in part on the first utterance and provides the first dialog response to the customer using a text-to-speech converter.

Abstract: An example computer-implemented method embodying the disclosed technology comprises digitally storing a plurality of digital objects comprising first type digital objects and second type digital objects, each digital object comprising an electronic digital representation of natural language text, and certain first type digital objects each being associated with exactly one second type digital object; programmatically generating a corpus of digital documents from the plurality of digital objects; programmatically embedding the electronic digital representation of natural language text of each first type digital object not associated with one of the second type digital objects, thereby generating a second set of vectors; programmatically determining, for each of the second set of vectors, a corresponding set of nearest neighbor vectors from the first set of vectors; programmatically generating recommendation data indicating potential new associations between first type digital objects and second type digital ob

Abstract: A network validation system is described which may perform operations such as generating, analyzing, verifying, correcting, recommending, and deploying language, symbols, etc., such as domain specific language, configured to allow users to express their intent on the configuration and operation of a network, such as a cloud-based network. The network validation system may provide domain specific language that includes rules, statements, symbols, data, etc., configured to convey the intent of users on the configuration and operation of networks for purposes such as configuring and/or validating communication paths, testing or setting associated network object configurations, and may be employed to report violations in such configurations relative to user intent of the one or more users. The network validation system may also be employed to monitor such domain specific language and generate telemetry signaling, for example, that a rule has or has not been violated, actions a user may take, etc.

Abstract: A device for multi-modal user input includes a processor configured to process first data received from a first input device. The first data indicates a first input from a user based on a first input mode. The first input corresponds to a command. The processor is configured to send a feedback message to an output device based on processing the first data. The feedback message instructs the user to provide, based on a second input mode that is different from the first input mode, a second input that identifies a command associated with the first input. The processor is configured to receive second data from a second input device, the second data indicating the second input, and to update a mapping to associate the first input to the command identified by the second input.

Abstract: A downscaled version of an audio decoding procedure may more effectively and/or at improved compliance maintenance be achieved if the synthesis window used for downscaled audio decoding is a downsampled version of a reference synthesis window involved in the non-downscaled audio decoding procedure by downsampling by the downsampling factor by which the downsampled sampling rate and the original sampling rate deviate, and downsampled using a segmental interpolation in segments of ¼ of the frame length.

Abstract: A downscaled version of an audio decoding procedure may more effectively and/or at improved compliance maintenance be achieved if the synthesis window used for downscaled audio decoding is a downsampled version of a reference synthesis window involved in the non-downscaled audio decoding procedure by downsampling by the downsampling factor by which the downsampled sampling rate and the original sampling rate deviate, and downsampled using a segmental interpolation in segments of 1/4 of the frame length.

Abstract: A downscaled version of an audio decoding procedure may more effectively and/or at improved compliance maintenance be achieved if the synthesis window used for downscaled audio decoding is a downsampled version of a reference synthesis window involved in the non-downscaled audio decoding procedure by downsampling by the downsampling factor by which the downsampled sampling rate and the original sampling rate deviate, and downsampled using a segmental interpolation in segments of ¼ of the frame length.