A dialogue system includes a processor configured to: generate a meaning representation corresponding to an input sentence by performing Natural Language Understanding on the input sentence, generate an output sentence corresponding to the input meaning representation based on Recurrent Neural network (RNN), and determine whether the input sentence cannot be processed using the natural language generator. The processor calculates a parameter representing a probability of outputting the input sentence when the meaning representation corresponding to the input sentence is input to the natural language generator, and determines whether the input sentence cannot be processed based on the calculated parameter.

Implementations described herein relate to an automated assistant that iteratively renders various GUI elements as a user iteratively provides a spoken utterance, or sequence of spoken utterances, corresponding to a request directed to the automated assistant. These various GUI elements can be dynamically adapted as the user iteratively provides the spoken utterance to assist the user with efficiently completing the request. In some implementations, a generic container graphical element associated with candidate intent(s) can be initially rendered at a display interface of a computing device and dynamically adapted with tailored container graphical elements as a particular intent is determined while the user iteratively provides the spoken utterance. In additional or alternative implementations, the tailored container graphical elements can include a current status of one or more settings associated with the computing device or additional computing device(s) such that the user can view the current status while completing the spoken utterance.

Embodiments of the present disclosure provide a method and apparatus for processing a speech. The method may include: acquiring an original speech; performing speech recognition on the original speech, to obtain an original text corresponding to the original speech; associating a speech segment in the original speech with a text segment in the original text; recognizing an abnormal segment in the original speech and/or the original text; and processing a text segment indicated by the abnormal segment in the original text and/or the speech segment indicated by the abnormal segment in the original speech, to generate a final speech. A speech segment in the original speech is associated with a text segment in the original text to realize visual processing of the speech.

The present disclosure provides a wireless earphone device and method for using the wireless earphone device. The wireless earphone device comprises a processing unit, a switch unit, a wireless transceiving unit, a language input unit, and a speaker unit. The switch unit is electrically connected to the processing unit. The wireless transceiving unit is electrically connected to the processing unit, transmitting wirelessly with the earphone. The language input unit is electrically connected to the processing unit. The speaker unit is electrically connected to the processing unit. While the earphone charging case is activated and switched to a translation mode by the switch unit, a first voice signal is inputted into the processing unit through the earphone, the processing unit processes the first voice signal into a second voice signal, and the second voice signal is emitted by the speaker unit.

One embodiment provides a method, comprising: receiving, at a digital assistant of an information handling device, a query from a user; providing, using the digital assistant, a response to the query; determining, during provision of the response, interest of the user in a topic contained within the response; and providing, based on the interest, extended information related to the topic. Other aspects are described and claimed.

An object is to give the user the impression that the system has sufficient dialogue capabilities. A humanoid robot (50) presents a first system speech to elicit information regarding a user's experience in a subject contained in a dialogue. A microphone (11) accepts a first user speech spoken by a user (101) after the first system speech has been spoken. When the first user speech is a speech that contains information regarding the user's experience, the humanoid robot (50) presents a second system speech to elicit information regarding the user's evaluation of the user's experience. The microphone (11) accepts a second user speech spoken by the user (101) after the second system speech has been spoken. When the second user speech is a speech that contains the user's positive or negative evaluation, the humanoid robot (50) presents a third system speech to sympathizes with the positive or negative evaluation.

A method for providing a service based on a user's voice includes steps of extracting a voice of a first user, generating text information or voice waveform information based on the voice of the first user, analyzing a disposition of the first user based on the text information and the voice waveform information, and then selecting a second user corresponding to the disposition of the first user based on the analysis result, providing the first user with a conversation connection service with the second user and acquiring information on a change in an emotional state of the first user based on conversation information between the first user and the second user, and re-selecting the second user corresponding to the disposition of the first user based on the acquired information on the change in the emotional state of the first user.

A wireless communication system uses a two-way radio as a user interface for a virtual assistant providing a user with access to an information system. The system can receive a request spoken into the two-way radio, convert the request from speech to text, and translate the text into a task that responds to the request. In various embodiments, the task is performed to produce a response in a form depending on the nature of the request.

Systems and methods for automatically determining a content item size may be based on a size of a viewport and a width of a parent element. A script may be configured to determine a size of a viewport, determine a width of a parent element of a resource, and determine a content item size based, at least in part, on the size of the view port and the width of the parent element. A dimension of the determined content item size may be used by a content item selection system to determine a set of content items. A content item selection system may select a content item from the determined set of content items and serve data to effect display of the selected content item in the parent element with the resource.

Mechanisms are provided for implementing a Question Answering (QA) system utilizing a trained generator of a generative adversarial network (GAN) that generates a bag-of-ngrams (BoN) output representing unlabeled data for performing a natural language processing operation. The QA system obtains a plurality of candidate answers to a natural language question, where each candidate answer comprises one or more ngrams. For each candidate answer, a confidence score is generated based on a comparison of the one or more ngrams in the candidate answer to ngrams in the BoN output of the generator neural network of the GAN. A final answer to the input natural language question is selected from the plurality of candidate answers based on the confidence scores associated with the candidate answers, and is output.