Abstract: A voice control system and a voice control method for an automatic door are provided. The voice control system includes a sound detection device, a storage device, a first determination circuit, a second determination circuit and a control circuit. The sound detection device detects a sound signal of a sound source, the storage device includes a voiceprint database that includes reference voiceprint features. The first determination circuit analyzes a voiceprint feature of the sound signal and compares the voiceprint feature with the reference voiceprint features. The second determination circuit determines whether a velocity of the sound source falls within a reference speed range according to a frequency variation of the sound signal that matches one of the voiceprint features. In response to the velocity of the sound source within the reference speed range, the control circuit controls the automatic door to be in an open state.

Abstract: Disclosed is an intelligent management system for a digital person dialogue based on Internet of Things. The system comprises a voice request question extraction module, configured to extract a voice request question input by a user and an input time point; a demand response time parsing module, configured to analyze a request urgency coefficient and a demand response time of the user; an adaptive response content search and determination module, configured to search and determine an adaptive response content; a dialogue scene recognition module, configured to recognize a dialogue scene; an adaptive dialogue intonation selection module, configured to select an adaptive dialogue intonation based on the dialogue scene; an adaptive dialogue language selection module, configured to determine an adaptive dialogue voice type; and a dialogue expression and implementation module, configured to perform a dialogue expression based on a dialogue platform.

Abstract: The present disclosure generally relates to decoding encoded files. More particularly, the present disclosure relates to systems and processes for determining the underlying language of encoded files having certain file formats with an undeterminable encoding. It may be difficult, time consuming, and costly to decode the files with undeterminable encodings as such files may require the language to be identified prior to decoding. Embodiments disclosed herein relate to determining the underlying language of the files by analyzing bit sequences in the encoded file and comparing the bit sequences against training data to determine matching patterns between the bit sequences in the file and the bit sequences known correspond to terms associated with a particular language.

Abstract: A computer system for extracting structured data from unstructured or semi-structured text in an electronic document, the system comprising: a graphical user interface configured to present to a user a graphical view of a document for use in training multiple data extraction models for the document, each data extraction model associated with a user defined question; a user input component configured to enable the user to highlight portions of the document; the system configured to present in association with each highlighted portion an interactive user entry object which presents a menu of question types to a user in a manner to enable the user to select one of the question types, and a field for receiving from the user a question identifier in the form of human readable text, wherein the question identifier and question type selected by the user are used for selecting a data extraction model, and wherein the highlighted portion of the document associated with the question identifier is used to train the sele

Abstract: A voice control method and apparatus for a device, a storage medium, and an electronic apparatus are provided. The method includes: acquiring a first voice feature of first voice data collected by a cleaning device, where the first voice data correspond to a first wake-up instruction sent by a use object, and the first wake-up instruction is used to wake up at least one of the cleaning device and a base station; acquiring a second voice feature of second voice data collected by the base station, where the second voice data correspond to the first wake-up instruction; and selecting a first device to be woken up from the cleaning device and the base station according to the first and second voice features, and waking up the first device, where the first device in a wake-up state is configured to respond to a voice instruction sent by the use object.

Abstract: A method uses natural language processing for visual analysis of a dataset. The method includes receiving a first natural language (NL) input directed to a data source, from a first client. The method also includes parsing the first NL input into tokens based on a grammar and the data source. The method also includes generating and outputting an intermediate NL response, to a second client, based on the tokens and output modality of the second client. In response to receiving a user input to provide missing information: the method also includes generating an input query based on the user input; and querying the data source using the input query, to obtain a result set. The method also includes generating and outputting, to the second client, a first NL output and a snapshot of a data visualization, based on the result set and the output modality of the second client.

Abstract: Apparatus (5) for assessing a quality of a communication session (3) between at least one first party (1) and at least one second party (2a, 2b . . . 2N), over a telecommunication network (4), comprising means for: monitoring (S1) said communication session by continuously receiving an audio stream associated with said communication session; converting (S2) language of said audio stream into text data; determining (S3), from said text data, at least first understandability quality features (UQFA, UQFG) and an information quality feature (IQF), said first understandability quality feature being representative of at least word articulation and grammar correctness within said language, and said information quality feature being representative of a comparison of the semantic content of said audio stream with a set of contents related to said audio stream; assessing (S4) said quality from said quality features.

Abstract: A method and electronic device for a vehicle are disclosed herein. The electronic device is mounted in the vehicle and includes a display, a memory storing voice commands, and a processor. The processor implements the method, including: obtaining at least one of vehicle driving information, occupant information, or display output information, generating one or more short commands by shortening one or more of the voice commands, based on the obtained at least one of the vehicle driving information, the occupant information and the display output information, and controlling the display to display one or more voice command guidance user interface (UI) displaying the one or more short commands.

Abstract: A system and method for creating accessibility of any website or application for people with sight, hearing or speech disabilities. The system and method can include receiving input of the website or the application to be accessed and an indicator as to specific disabilities a user, scoring the website or the application for its accessibility based on the specific disabilities of the user, and if the score is below a threshold, determining an alternative form for the input of the website or the application to accommodate the specific disabilities of the user.

Abstract: In various examples there is a computer-implemented method of database construction. The method comprises storing a knowledge graph comprising nodes connected by edges, each node representing a topic. Accessing a topic type hierarchy comprising a plurality of types of topics, the topic type hierarchy having been computed from a corpus of text documents. One or more text documents are accessed and the method involves labelling a plurality of the nodes with one or more labels, each label denoting a topic type from the topic type hierarchy, by, using a deep language model; or for an individual one of the nodes representing a given topic, searching the accessed text documents for matches to at least one template, the template being a sequence of words and containing the given topic and a placeholder for a topic type; and storing the knowledge graph comprising the plurality of labelled nodes.

Abstract: An apparatus and method are provided for processing a user input in an electronic device.

Abstract: A method of end-to-end speaker diarization (EESD) using neural speaker clustering, performed by at least one processor, is provided. The method includes generating a set of speech labels corresponding to a set of speakers based on an input stream. The speech labels indicate whether dialogue of a speaker is speech or non-speech. The method further includes generating dialogue based on the set of speakers, extracting speaker embeddings from the dialogue, mapping the speaker embeddings to a cluster identification (ID), an overlapped speech value, or a non-speech value based on a neural network, and outputting EESD labels based on the mapping.

Abstract: A natural language understanding (NLU) framework includes a modeling and optimization system that enables enhanced understanding and explainability to the operation of the NLU framework. The NLU framework includes a configuration vector storing settings of various components that may be applied during NLU inference of an utterance, such as which components should be activated or deactivated, as well as which numerical values (e.g., threshold values, coefficients, weight values) that are used by these components during operation. By using this configuration vector to systematically disable and adjust numerical parameters of the components of the NLU framework, and then determining the performance of the NLU framework in these configurations, the modeling and optimization system determines relationships between, as well as the relative importance of, the components of the NLU framework.

Abstract: Methods, apparatus, and computer readable media related to soliciting feedback from a user regarding one or more content parameters of a suggestion or other content provided by the automated assistant. The user's feedback may be used to influence future suggestions and/or other content subsequently provided, by the automated assistant in future dialog sessions, to the user and/or to other users. In some implementations, content is provided to a user by an automated assistant in a dialog session between the user and the automated assistant—and the automated assistant provides a prompt that solicits user feedback related to the provided content in a future dialog session between the user and the automated assistant. In some of those implementations, the prompt is provided following input from the user and/or output from the automated assistant, in the future dialog session, that is unrelated to the content provided in the previous dialog session.

Abstract: A missing semantics complementing method in the field of natural language processing in the artificial intelligence field is provided. The method includes: obtaining a question statement and a historical dialog statement; resolving a to-be-resolved item in the question statement based on the historical dialog statement and location information of the to-be-resolved item, to obtain a resolved question statement; determining whether a component in the question statement is ellipted, and if a component in the question statement is ellipted, complementing the ellipted component based on the historical dialog statement, to obtain a question statement after ellipsis resolution; merging the resolved question statement and the question statement after ellipsis resolution, to obtain a merged question statement; and determining a target complemented question statement from the resolved question statement, the question statement after ellipsis resolution, and the merged question statement.

Abstract: An eyewear device that performs diarization by segmenting spoken language into different speakers and remembering each speaker over the course of a session. The speech of each speaker is translated to text and the text of each speaker is displayed on an eyewear display. The text of each user has a different attribute such that the eyewear user can distinguish the text of different speakers. Examples of the text attribute can be a text color, font, and font size. The text is displayed on the eyewear display such that it does not substantially obstruct the user's vision.

Abstract: Predicting potential policy violations in a given data source (such as a set of documents) so that a deeper analysis can be performed on the set of documents to gain additional insights into the potential policy violation(s) that may be contained therein. In some instances, this prediction is done by performing a random sampling operation on the set of documents and collecting the metadata from these documents in order to determine whether or not the set of documents that are randomly sampled include a policy violation that can be remediated.

Abstract: An information processing apparatus includes an acquisition unit configured to acquire a first annotation that is for an addition target and is based on input from an operator, a comparison unit configured to compare the first annotation acquired by the acquisition unit and a second annotation that is a comparison target, a determination unit configured to determine whether there is a decrease in recognition accuracy of the operator based on the comparison by the comparison unit, and a warning unit configured to provide a warning in a case where the determination unit determines that there is a decrease in recognition accuracy of the operator.

Abstract: Debiasing pre-trained sentence encoders with probabilistic dropouts may be performed by various systems, services, or applications. A sentence may be received, where the words of the sentence may be provided as tokens to an encoder of a machine learning model. A token-wise correlation using semantic orientation may be determined to determine a bias score for the tokens in the input sentence. A probability of dropout that for tokens in the input sentence may be determined from the bias scores. The machine learning model may be trained or tuned based on the probabilities of dropout for the tokens in the input sentence.

Abstract: Techniques are disclosed for systems including techniques for multi-factor modelling for training and utilizing chatbot systems for natural language processing. In an embodiment, a method includes receiving a set of utterance data corresponding to a natural language-based query, determining one or more intents for the chatbot corresponds to a possible context for the natural language-based query and associated with a skill for the chatbot, generating one or more intent classification datasets, each intent classification dataset associated with a probability that the natural language query corresponds to an intent of the one or more intents, generating one or more transformed datasets each corresponding to a skill of one or more skills, determining a first skill of the one or more skills based on the one or more transformed datasets and processing, based on the determined first skill, the set of utterance data to resolve the natural language-based query.