Abstract: A service, in response to receiving a question in a natural language format, identifies one or more selected passages from a corpus that are relevant to a focus of the question from among multiple passages in the corpus. The service aligns one or more answer grammatical properties of one or more answers, selected from the one or more selected passages, to one or more question grammatical properties of the focus of the question. The service returns the one or more answers in response to the question.

Abstract: The present technology relates to an information processing device, an information processing method, a voice output device, and a voice output method that allow a user to hear a speech from a home agent unit regardless of where the user is. The voice output device outputs, on the basis of an image and noise from a predetermined noise source which are obtained in a unit capable of outputting a voice toward a user, information indicating hearing difficulty of a voice from the unit at a position of the user. The present technology can be applied to a household voice assistant device that performs a speech to a user.

Abstract: A management of user profiles comprises calculating, for each speaker model of at least one speaker model, a confidence measure representing a probability that the speaker model represents a speaker of a cluster of audio segments. A user profile associated with the speaker model is updated based on a user preference assigned to the cluster of audio segments if the confidence measure calculated for the speaker model represents a probability that is higher than a target probability. The embodiments achieve an efficient user profile management in a voice-controlled context but without the need for any dedicated enrollment sessions to train speaker models.

Abstract: According to one embodiment, an electronic device includes a transceiver and a hardware processor. The transceiver establishes a wired connection or a wireless connection between the electronic device and a wearable device wearable by a user. The hardware processor receives voice data generated by collecting speech of the user from the wearable device. The hardware processor performs a process to recognize one of one or more first commands from the voice data when a first mode is set as a voice recognition mode, performs a process to recognize one of second commands from the voice data when a second mode is set as the voice recognition mode, and repeatedly performs a process to recognize one of third commands from the voice data when a third mode is set as the voice recognition mode.

Abstract: Systems, devices, media, and methods are presented for generating a language detection model of a language analysis system. The systems and methods access a set of messages including text elements and convert the set of messages into a set of training messages. The set of training messages are configured for training a language detection model. The systems and methods train a classifier based on the set of training messages. The classifier has a set of features representing word frequency, character frequency, and a character ratio. The systems and methods generate a language detection model based on the classifier and the set of features.

Abstract: Provided is a sound event recognition method that may improve a sound event recognition performance using a correlation between difference sound signal feature parameters based on a neural network, in detail, that may extract a sound signal feature parameter from a sound signal including a sound event, and recognize the sound event included in the sound signal by applying a convolutional neural network (CNN) trained using the sound signal feature parameter.

Abstract: Described herein is a method for creating object-based audio content from a text input for use in audio books and/or audio play, the method including the steps of: a) receiving the text input; b) performing a semantic analysis of the received text input; c) synthesizing speech and effects based on one or more results of the semantic analysis to generate one or more audio objects; d) generating metadata for the one or more audio objects; and e) creating the object-based audio content including the one or more audio objects and the metadata. Described herein are further a computer-based system including one or more processors configured to perform said method and a computer program product comprising a computer-readable storage medium with instructions adapted to carry out said method when executed by a device having processing capability.

Abstract: The invention refers to a natural language processing system configured for receiving an input sequence ci of input words representing a first sequence of words in a natural language of a first text and generating an output sequence of output words representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of full contextual information around each word vi, wherein both preceding words v<i and following words v>i around each word vi are captured by using a bi-directional language modelling and a feed-forward fashion, wherein position dependent forward hidden layers {right arrow over (h)}i and backward hidden layers i for each word vi are computed.

Abstract: A speech interface device is configured to switch between languages, at the request of a user, in order to locally process utterances spoken in different languages, even in instances when a remote system is unavailable to, slower than, or otherwise less preferred than the speech interface device. For example, a user can request to set the language setting of the speech interface device to a second language, different from a first language to which the language setting of the device is currently set. Based on this user request, a local speech processing component of the device may load a language model(s) associated with the second language. The speech interface can also output voice prompts in the second language to manage the user's experience while a language update is in progress on the speech interface device.

Abstract: A conversation may be monitored in real time using a trained machine learning model to identify a desired outcome of a conversation and generate one or more phrases for accomplishing the desired outcome. A confidence score may also be determined for one or more phrases that indicates a likelihood that the one or more phrases may help accomplish the desired outcome of the conversation. In some examples, a confidence score may be based on whether an agent, a caller, or both responded unfavorably to a similar phrase used previously in another conversation. In other examples, a confidence score corresponding to one or more phrases may be based on whether a prior conversation in which one or more similar phrases was used resulted in the desired outcome being accomplished.

Abstract: Linguistic analysis methods and computer system for intelligently interacting with users in voice or text mode. The methods can improve the accuracy in recognizing user's physical or mental state when receiving user input expressions that are not in the form of a request or command, but in the form of a narrative or conversational statement, and generate relevant responses that address the user's needs, and perform tasks for the user when possible. The methods analyze the syntactic, semantic, and contextual attributes of terms in the user expressions, and handles ambiguous entities that may be the source of an intended action, or the target of such actions. Specially, methods for recognizing target entities represented by multi-word complex phrases are described and applied thus more appropriate machine responses can be determined when the input expression involves various types of attributes and different degrees of ambiguities.

Abstract: Embodiments provide for dialog based speech recognition by clustering a plurality of nodes comprising a dialog tree into at least a first cluster and a second cluster; creating a first dataset of natural language sentences for the first cluster and a second dataset of natural language sentences for the second cluster; generating a first specialized language model (LM) associated with the first cluster based on the first dataset; and generating a second specialized LM associated with the second cluster based on the second dataset, wherein the first specialized LM is different from the second specialized LM.

Abstract: Methods, systems and computer program products for operating a voice response system in a multiuser environment are provided. Aspects include receiving a voice command from a first user and determining a characteristic of how the voice command was received by the voice response system. Aspects also include obtaining a response preference of the first user and determining a response to the voice command. Aspects further include providing the response to the first user, wherein a manner in which the response is provided is determined based at least in part on the response preference of the first user and the characteristic of how the voice command was received.

Abstract: To provide an electronic device, which is carried by a user and is provided with a voice input unit, provided with a detection unit detecting a proximity state of the electronic device and the user and a control unit controlling the detection sensitivity of a voice input unit according to a detection result by the detection unit. Preferably, the detection unit detects a wearing state of the electronic device by the user and, when a non-wearing state where is detected by the detection unit, the control unit increases the detection sensitivity of the voice input unit to be higher than the detection sensitivity of the voice input unit in the wearing state.

Abstract: Systems and methods that access an online networked resource using a locator are disclosed. A first item of content on the networked resource is identified. A trigger rule comprising keywords and a sentiment classifier is accessed. A neural network, including input, hidden, and output layers, is used to assign a sentiment classification to the first item of content. The trigger rule, the sentiment classification, and identified keywords, are used to determine whether response content is to be posted to the online networked resource. In response to determining, using the trigger rule, the assigned sentiment classification, and keywords identified in the first item of content, that response content is to be posted to the online networked resource, the sentiment classification and identified keywords are used to select and/or generate a second item of content, and the second item of content is enabled to be posted to the online networked resource.

Abstract: Techniques for monitoring a conversation in real-time to detect attributes of a conversation, identifying a desired outcome of the conversation, and identifying voice modulations that may be applied to the agent's voice to help accomplish the desired outcome are disclosed. The system may identify voice modulations by comparing a current conversation to one or more prior conversations having desired outcomes similar to that of the current conversation. A trained machine learning model may select and apply voice modulations associated with accomplishing a desired outcome.

Abstract: A facility for representing a mandate occurring in an authority document with a control is described. For each of one or more controls in a set of existing controls, the facility determines a similarity score measuring the similarity of the mandate and the control; where the similarity score exceeds a similarity threshold, the facility links the mandate to the control. Where the mandate is not linked to any control in the set of controls, the facility adds a control to the set of controls that is based on the mandate, and links the mandate to the added control.

Abstract: It is depicts a method of speech recognition, sequentially executed by a processor on consecutive speech segments that comprises: obtaining digital information, which is a spectrogram representation, of a speech segment, and extracting from it speech features that characterizes the segment from the spectrogram representation. Then, a consistent structure segment vector based on the speech features is determined onto which machine learning is deployed to determine at least one label of the segment vector. A method of voice recognition and image recognition sequentially executed by a processor, on consecutive voice segments is also described. A system for executing speech, voice, and image recognition is also provided that comprises client devices to obtain and display information, a segment vector generator to determine a consistent structure segment vector based on features, and a machine learning server to determine at least one label of the segment vector.

Abstract: A dialogue system includes a response utterance selecting unit generating a response utterance original sentence to an input utterance; an input utterance emotion estimating unit estimating emotion of the input utterance by calculating input utterance emotion scores indicating degree of matching between the emotion represented by the input utterance and a plurality of emotions; and a response utterance modifying unit for calculating response utterance emotion scores of a response utterance original sentence as emotion scores for each of the plurality of emotions, modifying the response utterance original sentence by a method of modification determined by the values of input utterance emotion score and the response utterance emotion score, and thereby generating and outputting a response utterance.

Abstract: An electronic device is disclosed. The electronic device includes a memory configured to store a pronunciation dictionary including a plurality of words; and a processor configured to: obtain a second word based on a first word of the plurality of words; obtain a first text corpus related to the first word through web crawling of the first word and a second text corpus related to the second word through web crawling of the second word; and verify the second word based on a result of comparison of the first text corpus and the second text corpus.