Abstract: Determining a language for speech recognition of a spoken utterance received via an automated assistant interface for interacting with an automated assistant. Implementations can enable multilingual interaction with the automated assistant, without necessitating a user explicitly designate a language to be utilized for each interaction. Implementations determine a user profile that corresponds to audio data that captures a spoken utterance, and utilize language(s), and optionally corresponding probabilities, assigned to the user profile in determining a language for speech recognition of the spoken utterance. Some implementations select only a subset of languages, assigned to the user profile, to utilize in speech recognition of a given spoken utterance of the user.

Abstract: An artificial intelligence (AI) platform to support optimization of workload scheduling in a distributed computing environment. Unstructured data corresponding to one or more application artifacts related to a workload in the distributed computing environment is leveraged. NLP is applied to the unstructured data to identify one or more host requirements corresponding to the application artifacts. One or more hosts in the computing environment compatible with the identified host requirements are selectively identified and compatibility between the application artifacts and the identified hosts is assessed. The workload is selectively scheduled responsive to the selective host identification based on the assessed compatibility. The scheduled workload is selectively executed on at least one of the selectively identified hosts responsive to the assessment workload compatibility.

Abstract: Determining a dialog state of an electronic dialog that includes an automated assistant and at least one user, and performing action(s) based on the determined dialog state. The dialog state can be represented as one or more slots and, for each of the slots, one or more candidate values for the slot and a corresponding score (e.g., a probability) for each of the candidate values. Candidate values for a slot can be determined based on language processing of user utterance(s) and/or system utterance(s) during the dialog. In generating scores for candidate value(s) of a given slot at a given turn of an electronic dialog, various features are determined based on processing of the user utterance and the system utterance using a memory network. The various generated features can be processed using a scoring model to generate scores for candidate value(s) of the given slot at the given turn.

Abstract: Among other things, requests are received from voice assistant devices expressed in accordance with different corresponding protocols of one or more voice assistant frameworks. Each of the requests represents a voiced input by a user to the corresponding voice assistant device. The received requests are re-expressed in accordance with a common request protocol. Based on the received requests, responses to the requests are expressed in accordance with a common response protocol. Each of the responses is re-expressed according to a protocol of the framework with respect to which the corresponding request was expressed. The responses are sent to the voice assistant devices for presentation to the users.

Abstract: Methods, systems, and devices for asset discovery, user discovery, data classification, risk evaluation, and data/device security are described. The method includes retrieving data stored at one or more remote locations, summarizing the retrieved data at the one or more remote locations, transferring the summarized data from the one or more remote locations to the at least one computing device, processing the transferred data by the at least one computing device, discovering assets in technology environments, classifying data that resides on each asset of the discovered assets into a respective confidentiality group of multiple confidentiality groups, calculating one or more risk scores for the discovered assets or users of the discovered assets, or both, and performing a security action to protect data that resides on an asset of the discovered assets.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. An intelligent automated assistant receives a user input and generates a set of one or more token sequences based on the user input. The set of one or more token sequences are interpreted to generate a plurality of candidate interpretations each including a corresponding action and metadata associated with the action. A top candidate interpretation is selected from the plurality of candidate interpretations, and the corresponding action is performed based on the associated metadata.

Abstract: Embodiments of the present invention relate to the field of terminal technologies, and provide a method and an apparatus for displaying a candidate word, and a graphical user interface to improve efficiency of a user in entering information by using an input method. The method is applied to a scenario in which a user enters information by using an input method. The method includes: determining a type of an application that invokes the input method; determining, according to the type, dimension information corresponding to the type; determining, according to the dimension information, a lexicon corresponding to the dimension information; and displaying, in a default candidate option area of the input method, at least one candidate word that is in the lexicon and meets a preset condition.

Abstract: A voice-controlled question answering system that is capable of answering questions using both a knowledge base and a search engine. The knowledge base is used to answer questions when answers to those questions are contained in the knowledge base. If an answer using the knowledge base is unavailable, and if the question is suitable for answering using an unstructured search approach, the system may obtain an answer using a search engine. The search engine results may be processed to obtain an answer to the question suitable for output using a voice user interface.

Abstract: Provided is a method and system for expanding to an everyday language using a word vectorization technique based on social network content. A content providing method includes collecting social network content on the Internet; expanding corresponding content information to a word set of words included in the social network content with respect to target content that is to be serviced to a client; and providing the target content to the client with respect to user information associated with the client using the word set.

Abstract: A system and method for implementing slot-relation extraction for a task-oriented dialogue system that includes implementing dialogue intent classification machine learning models that predict a category of dialogue of a single utterance based on an input of utterance data relating to the single utterance, wherein the category of dialogue informs a selection of slot-filling machine learning models; implementing the slot-filling machine learning models that predict slot classification labels for each of a plurality of slots within the utterance based on the input of the utterance data; implementing a slot relation extraction machine learning model that predicts semantic relationship classifications between two or more distinct slots of tokens of the utterance; and generating a response to the single utterance or performing actions in response to the single utterance based on the semantic relationship classifications between the distinct pairings of the two or more distinct slots of the single utterance.

Abstract: Documents in source natural languages are translated into target natural languages using a computer-implemented translation that is configured to operate within the domain of the subject matter of the documents that imposes specialized requirements for translation and readability. Subject matter specific documents typically include domain-specific terminology, are subject to various regulatory guidelines, and have different readability requirements depending on the intended reader. The computer-implemented translation applies machine-learning techniques that deconstruct elements of the subject matter specific document into a standard data structure and perform pre-processing steps to tokenize digitized document text to identify the correct sentence structure and syntax for the target natural language to optimize translation by, e.g., a neural machine translation engine.

Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes selecting at least one set of style specifications for transforming at least a portion of input text. The at least one set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of at least a portion of the input text, and weights for each of a set of linguistic aspects for transformation of at least a portion of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the at least one set of style specifications utilizing at least one unsupervised neural network.

Abstract: A personal assistant device configured to control companion devices may include a memory configured to maintain a companion device library including a plurality of companion device each associated with at least one long-name, short-cut name and companion device room location, and a processor. The processor may be configured to receive a user command from a microphone, extract a companion device name and action from the user command, determine whether the companion device name includes a unique name, and command a companion device associated with the unique name to perform the action from the user command in response to the user command including the unique name.

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

Abstract: Interactive content containing audio or video may be provided in conjunction with non-interactive content containing audio or video to enhance user engagement and interest with the contents and to increase the effectiveness of the distributed information. Interactive content may be directly inserted into the existing, non-interactive content. Additionally or alternatively, interactive content may be streamed in parallel to the existing content, with minimal modification to the existing content. For example, the server may monitor content from a content provider; detect an event (e.g., a marker embedded in the content stream, or in a data source external to the content stream); upon detecting the event, play interactive content at a designated time while silencing the content stream of the content provider (e.g., by muting, pausing, playing silence.) The marker may be a sub-audible tone or metadata associated with the content stream. The user may respond to the interactive content by voice.

Abstract: Utilizing an adaptive multichannel technique to mitigate reverberation present in received audio signals, prior to providing corresponding audio data to one or more additional component(s), such as automatic speech recognition (ASR) components. Implementations disclosed herein are “adaptive”, in that they utilize a filter, in the reverberation mitigation, that is online, causal and varies depending on characteristics of the input. Implementations disclosed herein are “multichannel”, in that a corresponding audio signal is received from each of multiple audio transducers (also referred to herein as “microphones”) of a client device, and the multiple audio signals (e.g., frequency domain representations thereof) are utilized in updating of the filter—and dereverberation occurs for audio data corresponding to each of the audio signals (e.g., frequency domain representations thereof) prior to the audio data being provided to ASR component(s) and/or other component(s).

Abstract: Computer-based processes are disclosed for analyzing and improving document readability. Document readability is improved by using rules and associated logic to automatically detect various types of writing problems and to make and/or suggest edits for eliminating such problems. Many of the rules seek to generate more concise formulations of the analyzed sentences, such as by eliminating unnecessary words, rearranging words and phrases, and making various other types of edits. Proposed edits can be conveyed, e.g., through a word processing platform, by changing the visual appearance of text to indicate how the text would appear with (or with and without) the edit.

Abstract: An information processing apparatus includes an acquiring unit, a detecting unit, and a voice command unit. The acquiring unit acquires voice information of a speaker. The detecting unit detects operation related to speech by the speaker. The voice command unit performs a voice command in accordance with the voice information acquired by the acquiring unit after the detecting unit detects the operation.

Abstract: A system and a method for obtaining a photo-realistic video from a text. The method includes: providing the text and an image of a talking person; synthesizing a speech audio from the text; extracting an acoustic feature from the speech audio by an acoustic feature extractor; and generating the photo-realistic video from the acoustic feature and the image by a video generation neural network. The video generating neural network is pre-trained by: providing a training video and a training image; extracting a training acoustic feature from training audio of the training video by the acoustic feature extractor; generating video frames from the training image and the training acoustic feature by the video generation neural network; and comparing the generated video frames with ground truth video frames using generative adversarial network (GAN). The ground truth video frames correspond to the training video frames.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes receiving two or more data sets each representing speech of a corresponding individual attending an internet-based social networking video conference session, decoding the received data sets to produce corresponding text for each individual attending the internet-based social networking video conference, and detecting characteristics of the session from a coalesced transcript produced from the decoded text of the attending individuals for providing context to the internet-based social networking video conference session.