Abstract: Embodiments include systems and methods for receiving an action item trigger by a user of a conferencing application; and in response to receiving the action item trigger, generating spoken words from audio data of a session of the conferencing application; normalizing the spoken words; generating higher-level representations of the normalized spoken words; determining semantic similarities of the higher-level representations of the normalized spoken words and higher level representations of normalized action words of an action word list; ranking options for top spoken words and action words based at least in part on the semantic similarities; identifying candidates for action words and/or phrases from the top spoken words and action words; and parsing the candidates to generate one or more action items.

Abstract: A speech interaction method includes: acquiring speech information of a user; determining a task list corresponding to the speech information, the task list comprising at least two ordered tasks; and for each task in the at least two ordered tasks, responsive to that a next task of a present task is a question-answer task, querying and sending response information of the next task to a user terminal before execution time of the next task arrives, such that the user terminal outputs the response information when the execution time of the next task arrives.

Abstract: Disclosed is a voice recognition device and method. According to the disclosure, the voice recognition device, upon failing to grasp the intent of the user's utterance from the original utterance which is divided into a head utterance and a tail utterance, figures out the intent from the head utterance to thereby complete the original utterance and provides the result of voice recognition processing on the original utterance. According to an embodiment, the voice recognition device may be related to artificial intelligence (AI) modules, robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

Abstract: A method, the method includes determining a target segment partially overlapping a preceding segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match. A portion overlapping the preceding segment in the target segment is greater than or equal to 8.3% of the target segment.

Abstract: A system configured to enable remote control to allow a first user to provide assistance to a second user. The system may receive a command from the second user granting remote control to the first user, enabling the first user to initiate a voice command on behalf of the second user. In some examples, the system may enable the remote control by treating a voice command originating from the first user as though it originated from the second user instead. For example, the system may receive the voice command from a first device associated with the first user but may route the voice command as though it was received by a second device associated with the second user.

Abstract: A speech-processing system may provide access to multiple virtual assistants via one or more voice-controlled devices. Each assistant may leverage language processing and language generation features of the speech-processing system, while handling different commands and/or providing access to different back applications. Each assistant may be associated with its own voice and/or speech style, and thus be perceived as having a particular “personality.” In some situations, a user may invoke a first assistant, e.g., with a wakeword or button press, and provide a command that the speech-processing system may determine will be better handled by a second assistant. The speech-processing system may thus call on a component to generate plan data describing one or more operations for the speech-processing system to execute to handoff the command to the second assistant and provide the user with indications of which assistant will handle the command.

Abstract: An output apparatus according to the present application includes a prediction unit and an output unit. The prediction unit predicts whether or not waveform information having a predetermined context is generated on the basis of detection information detected by a predetermined detection device. The output unit outputs waveform information having an opposite phase to the waveform information having the predetermined context in a case where it has been predicted that the waveform information having the predetermined context is generated.

Abstract: The present disclosure relates to a system, method, and computer program for extracting utterances corresponding to a user problem statement in a conversation between a human agent and a user. The system obtains a set of utterances from a natural language conversation between the human agent and the user. The system uses a problem-statement classifier to obtain machine-generated predictions as to whether each natural language utterance in the set relates to a problem statement. The system selects one or more utterances from the set as corresponding to a problem statement based on the predictions. The system provides the selected utterances to a downstream system for further processing. In certain embodiments, the problem statement classifier includes an encoder that creates an utterance embedding for each utterance and a prediction module that uses the utterance embeddings to predict whether each utterance corresponds to a user problem statement.

Abstract: Systems and methods for creating chatbot-enabled web forms and workflows, the method comprising, mapping web forms and workflows to intents, wherein the web forms have required fields to be completed and the workflows have required tasks to be performed; mapping the required fields and the required tasks to entities for the intents that map to the web forms and the workflows; mapping utterances to complete the required fields and perform the required tasks to the intents and the entities that map to the web forms and the workflows; and creating chatbots configured to assist users to complete the required fields and perform the required tasks using the utterances, the intents and the entities that map to the web forms and the workflows.

Abstract: Aspects of the subject technology relate to a method for using a voice command for multiple computing devices. First voice input data is received from a first computing device associated with a user account, where the first voice input data comprises a first voice command captured at the first computing device. Second voice input data is received from a second computing device associated with the user account where the second voice input data comprises a second voice command captured at the second computing device. An intended voice command is determined based on the obtained first and second voice input data. Based on the intended voice command, a first target computing device is determined. First instructions associated with the intended voice command are provided to the first target computing device for execution.

Abstract: Various embodiments disclosed herein provide techniques for performing incremental natural language understanding on a natural language understanding (NLU) system. The NLU system acquires a first audio speech segment associated with a user utterance. The NLU system converts the first audio speech segment into a first text segment. The NLU system determines a first intent based on a text string associated with the first text segment, wherein the text string represents a portion of the user utterance. The NLU system generates a first response based on the first intent prior to when the user utterance completes.

Abstract: Embodiments relate to an artificial intelligence (AI) computer platform to incorporate synthetic data and ground truth data, and to promote diversity and accuracy in generating the synthetic data. Synthetic questions are generated by a question generator in response to semantically related ground truth passage and answer data. Each generated question is presented to an answer generator together with the semantically related ground truth passage. Each synthetic question is evaluated with respect to its diversity from previous synthetic questions generated for the same ground truth passage and answer data. Each synthetic question is also evaluated with respect to the accuracy of the answer generated by the answer generator. A reward function that captures both accuracy and diversity of each synthetic question is leveraged to selectively modify the question generator, with the selective modification(s) directed at increasing textual diversity and maintaining accuracy of the generated synthetic questions.

Abstract: Systems and methods for optimizing voice detection via a network microphone device (NMD) based on a selected voice-assistant service (VAS) are disclosed herein. In one example, the NMD detects sound via individual microphones and selects a first VAS to communicate with the NMD. The NMD produces a first sound-data stream based on the detected sound using a spatial processor in a first configuration. Once the NMD determines that a second VAS is to be selected over the first VAS, the spatial processor assumes a second configuration for producing a second sound-data stream based on the detected sound. The second sound-data stream is then transmitted to one or more remote computing devices associated with the second VAS.

Abstract: A method for providing a context awareness service is provided. The method includes defining a control command for the context awareness service depending on a user input, triggering a playback mode and the context awareness service in response to a user selection, receiving external audio through a microphone in the playback mode, determining whether the received audio corresponds to the control command, and executing a particular action assigned to the control command when the received audio corresponds to the control command.

Abstract: The disclosure relates to an artificial intelligence (AI) system using a learned AI model according to at least one of machine learning, neural network, or a deep learning algorithm and applications thereof. In the disclosure, a control method of an electronic apparatus is provided. The control method comprises the steps of: displaying an image including at least one object receiving a voice; inputting the voice to an AI model learned by an AI algorithm to identify an object related to the voice among the at least one object included in the image and acquire tag information about the identified object; and providing the obtained tag information.

Abstract: A method, the method includes determining a target segment from a speech signal, determining a target character sequence corresponding to the target segment by decoding the target segment, identifying a first overlapping portion between the target character sequence and a preceding character sequence based on an edit distance, and merging the target character sequence and the preceding character sequence based on the first overlapping portion. A cost applied to the edit distance is determined based on any one or any combination of any two or more of a type of operation performed at the edit distance, whether characters to be operated are located in the first overlapping portion, and whether the characters to be operated match.

Abstract: Embodiments are directed to a system, computer program product, and method for text mining, and dynamic facet and facet value management and application to a document collection. Two or more words from a first document collection are extracted, with the extracted words being associated with an applied annotation. At least one word is selected from the extracted words, designated as a facet, and a value is selectively added to the facet. An analysis of the added value is dynamically performed, and a dictionary with the annotation, facet, and values is constructed and the dictionary is applied to the document collection. A targeted list of documents is returned from the dictionary application to the document collection.

Abstract: Techniques are disclosed that enable automating user interface input by generating a sequence of actions to perform a task utilizing a multi-agent reinforcement learning framework. Various implementations process an intent associated with received user interface input using a holistic reinforcement policy network to select a software reinforcement learning policy network. The sequence of actions can be generated by processing the intent, as well as a sequence of software client state data, using the selected software reinforcement learning policy network. The sequence of actions are utilized to control the software client corresponding to the selected software reinforcement learning policy network.

Abstract: Methods and systems for training and/or using a language selection model for use in determining a particular language of a spoken utterance captured in audio data. Features of the audio data can be processed using the trained language selection model to generate a predicted probability for each of N different languages, and a particular language selected based on the generated probabilities. Speech recognition results for the particular language can be utilized responsive to selecting the particular language of the spoken utterance. Many implementations are directed to training the language selection model utilizing tuple losses in lieu of traditional cross-entropy losses. Training the language selection model utilizing the tuple losses can result in more efficient training and/or can result in a more accurate and/or robust model—thereby mitigating erroneous language selections for spoken utterances.

Abstract: A method for administering a plurality of Things in a knowledge base includes receiving a statement. A first verb action parses the statement into a parsed Thing. A second verb action evaluates the parsed Thing using a vocabulary, and computes and sets a performable statement Thing having a verb in the vocabulary representing a performable action. A third verb action performs the performable action upon a target Thing, wherein the vocabulary encompasses a set of performable action Things and a set of target Things a performable action Thing can act upon.