Abstract: Examples of the present disclosure describe systems and methods for automatically assisting conversations using a graph database. In order to minimize misunderstanding of words and phrases used by participants during a conversation, phrases from the conversation may be received by conversation assistance application as the conversation takes place. Entities may be extracted from the phrase based on natural language recognition according to a domain context of the participant being assisted. One or more tags may be looked up from a graph database, and may be provided to the participant as a list of hashtags related to the conversation. Links to documents may be extracted based on the tags for the participant for viewing during the conversation.

Abstract: A method executed by a computing device includes determining a set of identigens for each phrase word of a phrase to produce sets of identigens. A set of identigens of the sets of identigens represents one or more different meanings of a phrase word of the phrase. The method further includes obtaining sensor information for one or more phrase words of the phrase. The method further includes selecting an identigen of a first set of identigens based on the sensor information to produce a first identigen selection for the first set of identigens having a selected meaning of one or more different meanings of the first phrase word. The method further includes interpreting remaining sets of identigens of the sets of identigens to produce an entigen group so that the entigen group represents a most likely meaning interpretation of the phrase.

Abstract: A natural language understanding (NLU) framework includes a lookup source system having one or more lookup sources. Each lookup source includes a respective source data representation that is compiled from respective source data. Once compiled, a user utterance can be submitted to the lookup source system, which generates segmentations of the user utterance. Each segmentation generally includes a collection of non-overlapping segments, and each segment generally describes how tokens of the user utterance can be grouped together and matched to the states of the source data representations. During lookup source inference, matches can be made to produced states or using fuzzy matchers that have corresponding of scoring adjustments. These scoring adjustments may be used by a segmentation scoring subsystem, potentially in combination with one or more additional segmentation scoring plugins, to score and rank the segmentations determined by the lookup source system for the user utterance.

Abstract: An audio decoder decodes a bit stream of encoded audio data, which bit stream represents a sequence of audio sample values and includes a plurality of frames, wherein each frame includes associated encoded audio sample values. The audio decoder includes a determiner configured to determine whether a frame of the encoded audio data is a special frame including encoded audio sample values associated with the special frame and additional information, wherein the additional information include encoded audio sample values of a number of frames preceding the special frame, wherein the encoded audio sample values of the preceding frames are encoded using the same codec configuration as the special frame, wherein the number of preceding frames is sufficient to initialize the decoder to be in a position to decode the audio sample values associated with the special frame if the special frame is the first frame upon start-up of the decoder.

Abstract: An audio decoder decodes a bit stream of encoded audio data, which bit stream represents a sequence of audio sample values and includes a plurality of frames, wherein each frame includes associated encoded audio sample values. The audio decoder includes a determiner configured to determine whether a frame of the encoded audio data is a special frame including encoded audio sample values associated with the special frame and additional information, wherein the additional information include encoded audio sample values of a number of frames preceding the special frame, wherein the encoded audio sample values of the preceding frames are encoded using the same codec configuration as the special frame, wherein the number of preceding frames is sufficient to initialize the decoder to be in a position to decode the audio sample values associated with the special frame if the special frame is the first frame upon start-up of the decoder.

Abstract: According to the present invention, provided is a method for collecting filtered text data, comprising the steps in which: a computing device acquires first text data and records the first text data in a text data pool; the computing device acquires second text data; the computing device performs a calculation in a deep learning model by using the first text data and the second text data as input values and calculates a first feature vector corresponding to the first text data and a second feature vector corresponding to the second text data; and the computing device compares the degree of similarity between the first feature vector and the second feature vector, and records the second text data in the text data pool when the degree of similarity is less than a predetermined value.

Abstract: A method for an automated speech recognition (ASR) model for unifying streaming and non-streaming speech recognition including receiving a sequence of acoustic frames. The method includes generating, using an audio encoder of an automatic speech recognition (ASR) model, a higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The method further includes generating, using a joint encoder of the ASR model, a probability distribution over possible speech recognition hypothesis at the corresponding time step based on the higher order feature representation generated by the audio encoder at the corresponding time step. The audio encoder comprises a neural network that applies mixture model (MiMo) attention to compute an attention probability distribution function (PDF) using a set of mixture components of softmaxes over a context window.

Abstract: Method for editorializing digital audiovisual or audio recording content of an oral presentation given by a speaker using a presentation support enriched with tags and recorded in the form of a digital audiovisual file. This method comprises written transcription of the oral presentation with indication of a time code for each word, comparative automatic analysis of this written transcription and of the tagged presentation support, transposition of the time codes from the written transcription to the tagged presentation support, identification of the tags and of the time codes of the presentation support, and marking of the digital audiovisual file with the tags and time codes, so as to generate an enriched digital audiovisual file.

Abstract: The disclosed technology relates to methods, accent conversion systems, and non-transitory computer readable media for real-time accent conversion. In some examples, a set of phonetic embedding vectors is obtained for phonetic content representing a source accent and obtained from input audio data. A trained machine learning model is applied to the set of phonetic embedding vectors to generate a set of transformed phonetic embedding vectors corresponding to phonetic characteristics of speech data in a target accent. An alignment is determined by maximizing a cosine distance between the set of phonetic embedding vectors and the set of transformed phonetic embedding vectors. The speech data is then aligned to the phonetic content based on the determined alignment to generate output audio data representing the target accent.

Abstract: A text adjustment method includes: obtaining a to-be-processed text; determining whether to adjust the to-be-processed text according to the to-be-processed text and a context text of the to-be-processed text; in response to determining to adjust the to-be-processed text, determining adjustment character information and adjustment position information of the to-be-processed text according to the context text; and determining an adjusted to-be-processed text according to the adjustment character information and the adjustment position information.

Abstract: Implemented is a configuration of being able to reliably notify a device characteristic to a user by naturally generating and outputting a system speech including the device characteristic during an interaction with the user. The configuration includes a data processing section that generates and outputs a system speech including device characteristic information. The data processing section selects device characteristic information that is relevant to what is talked about during an interaction between the user and the information processing device, and generates and outputs a system speech including the selected device characteristic information. The data processing section receives an input of information of a user selection made to an option presented to the user, includes device characteristic information that is relevant to the inputted selection information into a system speech to be executed in an interaction with the user, and outputs the system speech.

Abstract: Provided is a method of performing automatic interpretation based on speaker separation by a user terminal, the method including: receiving a first speech signal including at least one of a user speech of a user and a user surrounding speech around the user from an automatic interpretation service providing terminal, separating the first speech signal into speaker-specific speech signals, performing interpretation on the speaker-specific speech signals in a language selected by the user on the basis of an interpretation mode, and providing a second speech signal generated as a result of the interpretation to at least one of a counterpart terminal and the automatic interpretation service providing terminal according to the interpretation mode.

Abstract: A method for performing a query based on a natural language voice input is provided. The method includes receiving, via a microphone, a voice input of a user, and converting the voice input into a first text data object. The method further includes converting the first text data object into a first technical language object using AI, and submitting a query based on the first technical language object. A query result in a second technical language object is retrieved in response to the query, and the query result is converted into a second text data object using AI. The method further converts the second text object into a voice data object indicating the query result, and outputs a voice signal to provide the information of the query result in a natural language form to the user.

Abstract: Methods and systems for managing and transmitting content are disclosed. A sample method can comprise determining signal-to-noise ratio information relating to one or more data blocks and determining a threshold signal-to-noise ratio. At least one of the one or more data blocks can be requested based upon respective signal-to-noise ratio information and the threshold signal-to-noise ratio.

Abstract: Remote automated assistant component(s) generate client device notification(s) based on a received IoT state change notification that indicates a change in at least one state associated with at least one IoT device. The generated client device notification(s) can each indicate the change in state associated with the at least one IoT device, and can optionally indicate the at least one IoT device. Further, the remote automated assistant component(s) can identify candidate assistant client devices that are associated with the at least one IoT device, and determine whether each of the one or more of the candidate assistant client device(s) should render a corresponding client device notification.

Abstract: An audio decoder decodes a bit stream of encoded audio data, which bit stream represents a sequence of audio sample values and includes a plurality of frames, wherein each frame includes associated encoded audio sample values. The audio decoder includes a determiner configured to determine whether a frame of the encoded audio data is a special frame including encoded audio sample values associated with the special frame and additional information, wherein the additional information include encoded audio sample values of a number of frames preceding the special frame, wherein the encoded audio sample values of the preceding frames are encoded using the same codec configuration as the special frame, wherein the number of preceding frames is sufficient to initialize the decoder to be in a position to decode the audio sample values associated with the special frame if the special frame is the first frame upon start-up of the decoder.

Abstract: The present invention includes steps of loading a website project; counting a word count of keywords of the website project for obtaining a word sum of the website project; respectively counting a first anchor word count for each of the anchor types to obtain a first anchor word sum for each of the anchor types; respectively dividing each of the first anchor word sums of each of the anchor types by the word sum to obtain multiple first internal anchor type percentages of the multiple anchor types; loading multiple first default anchor type percentages; for each of the anchor types, when the first internal anchor type percentage is greater than or equal to the first default anchor type percentage, marking the first internal anchor type percentage, and displaying results to prevent over-modifying the keywords corresponding to the marked anchor type, thus keeping the website project from being blacklisted.

Abstract: An audio decoder decodes a bit stream of encoded audio data, which bit stream represents a sequence of audio sample values and includes a plurality of frames, wherein each frame includes associated encoded audio sample values. The audio decoder includes a determiner configured to determine whether a frame of the encoded audio data is a special frame including encoded audio sample values associated with the special frame and additional information, wherein the additional information include encoded audio sample values of a number of frames preceding the special frame, wherein the encoded audio sample values of the preceding frames are encoded using the same codec configuration as the special frame, wherein the number of preceding frames is sufficient to initialize the decoder to be in a position to decode the audio sample values associated with the special frame if the special frame is the first frame upon start-up of the decoder.

Abstract: An electronic device for providing content including an image and a voice is disclosed. The electronic device comprises: a display configured to display an image; a memory in which a voice recognition module including various executable instructions is stored; and a processor configured to acquire expected words that will possibly be included in a voice, based on information about content, using the expected words to perform voice recognition for the voice through the voice recognition module, and displaying, on the display, text converted from the voice based on the voice recognition.

Abstract: An audio decoder decodes a bit stream of encoded audio data, which bit stream represents a sequence of audio sample values and includes a plurality of frames, wherein each frame includes associated encoded audio sample values. The audio decoder includes a determiner configured to determine whether a frame of the encoded audio data is a special frame including encoded audio sample values associated with the special frame and additional information, wherein the additional information include encoded audio sample values of a number of frames preceding the special frame, wherein the encoded audio sample values of the preceding frames are encoded using the same codec configuration as the special frame, wherein the number of preceding frames is sufficient to initialize the decoder to be in a position to decode the audio sample values associated with the special frame if the special frame is the first frame upon start-up of the decoder.