Abstract: Systems and methods are disclosed for generating internal state representations of a neural network during processing and using the internal state representations for classification or search. In some embodiments, the internal state representations are generated from the output activation functions of a subset of nodes of the neural network. The internal state representations may be used for classification by training a classification model using internal state representations and corresponding classifications. The internal state representations may be used for search, by producing a search feature from an search input and comparing the search feature with one or more feature representations to find the feature representation with the highest degree of similarity.

Abstract: Features are disclosed for detecting words in audio using contextual information in addition to automatic speech recognition results. A detection model can be generated and used to determine whether a particular word, such as a keyword or “wake word,” has been uttered. The detection model can operate on features derived from an audio signal, contextual information associated with generation of the audio signal, and the like. In some embodiments, the detection model can be customized for particular users or groups of users based usage patterns associated with the users.

Abstract: Disclosed is a speech recognition method performed by one or more processors of a computing device, the speech recognition method including: performing first speech recognition on voice information to obtain first text information on the voice information; receiving feedback regarding the first text information; and generating final text information for the voice information based on the received feedback, in which the first speech recognition includes real-time speech recognition, and is performed through a neural network model of a first structure.

Abstract: One embodiment provides a method for predicting a next action in a conversation system that includes obtaining, by a processor, information from conversation logs and a conversation design. The processor further creates a dialog graph based on the conversation design. Weights and attributes for edges in the dialog graph are determined based on the information from the conversation logs and adding user input and external context information to an edge attributes set. An unrecognized user input is analyzed and a next action is predicted based on dialog nodes in the dialog graph and historical paths. A guiding conversation response is generated based on the predicted next action.

Abstract: The present disclosure provides a method, apparatus, electronic device and readable storage medium for translation and relates to translation technologies. In the embodiments of the present disclosure, the at least one knowledge element is obtained according to associated information of content to be translated, and respective knowledge element in the at least one knowledge element comprise an element of the first language type and an element of the second language type so that the at least one knowledge element can be used to obtain a translation result of the content to be translated. Since the at least one knowledge element obtained in advance is taken as global information of the translation task of this time, it can be ensured that the translation result of the same content to be translated is consistent, thereby improving the quality of the translation result.

Abstract: Disclosed is a voice recognition method and apparatus using artificial intelligence. A voice recognition method using artificial intelligence may include: generating a utterance by receiving a voice command of a user; obtaining a user's intention by analyzing the generated utterance; deriving an urgency level of the user on the basis of the generated utterance and prestored user information; generating a first response in association with the user's intention; obtaining main vocabularies included in the first response; generating a second response by using the main vocabularies and the urgency level of the user; determining a speech rate of the second response on the basis of the urgency level of the user; and outputting the second response according to the speech rate by synthesizing the second response to a voice signal.

Abstract: A speech recognition method includes receiving speech data, obtaining, from the received speech data, a candidate text including at least one word and a phonetic symbol sequence associated with a pronunciation of a target word included in the received speech data, using a speech recognition model, replacing the phonetic symbol sequence included in the candidate text with a replacement word corresponding to the phonetic symbol sequence, and determining a target text corresponding to the received speech data based on a result of the replacing.

Abstract: A method, an electronic device and a readable storage medium for creating a label marking model are disclosed. The method for creating the label marking model includes: obtaining text data and determining a word or phrase to be marked in the text data; according to the word or phrase to be marked, constructing a first training sample of the text data corresponding to a word or phrase replacing task and a second training sample corresponding to a label marking task; training a neural network model with a plurality of the first training samples and a plurality of the second training samples, respectively, until a loss function of the word or phrase replacing task and a loss function of the label marking task satisfy a preset condition, to obtain the label marking model.

Abstract: An autocorrelation calculation unit 21 calculates an autocorrelation RO(i) from an input signal. A prediction coefficient calculation unit 23 performs linear prediction analysis by using a modified autocorrelation R?O(i) obtained by multiplying a coefficient wO(i) by the autocorrelation RO(i). It is assumed here, for each order i of some orders i at least, that the coefficient wO(i) corresponding to the order i is in a monotonically increasing relationship with an increase in a value that is negatively correlated with a fundamental frequency of the input signal of the current frame or a past frame.

Abstract: A voice command recognition device and a method thereof are provided. The voice command recognition device includes a processor that registers one or more voice commands selected by analysis of one or more voice commands repeatedly used by a user or a voice command utterance pattern of the user to generate one package command and a storage storing data or an algorithm for speech recognition by the processor.

Abstract: An embodiment of the present invention comprises: a communication module for communicating with at least one external device; a microphone for receiving a user utterance; a memory for storing performance mode information having been configured in the electronic device; and a processor electrically connected to the communication module, the microphone, and the memory, wherein the processor is configured to: receive, through the microphone, a second user utterance associated with task execution; transmit first data associated with the second user utterance to an external device; receive, from the external device, second data associated with at least a part of processing of the first data; identify a first work load allocated to the electronic device at the time of receiving the second data; and compare a second work load required for processing the second data and the first work load, so as to control the performance mode. In addition, various embodiments recognized through the specification are possible.

Abstract: Provided is an information processing apparatus that has an utterance function or controls the utterance function. The information processing apparatus includes a sending unit that sends interactive information regarding a voice agent, a receiving unit that receives interactive information regarding another voice, and a control unit that controls an utterance timing of the voice agent on the basis of the interactive information regarding another voice agent received by the receiving unit. The control unit causes utterance by the voice agent to stand by on the basis of the interactive information received from another voice agent. Moreover, the control unit causes the interactive information to be continuously sent during the utterance by the voice agent and during interaction between the voice agent and a user.

Abstract: Desired vehicle destinations may be determined from spoken dialogs. A speech input may be received from a user through a voice user interface. Current utterance variables may be obtained by tokenizing the user speech input. One or more of a plurality of utterance templates for a reply to the user speech input may be determined by a trained automatic agent based on the plurality of current utterance variables. One of a plurality of Application Programming Interfaces (API) to call and one or more parameters for the API to call with may be determine by the trained automatic agent based on the plurality of current utterance variables. A response may be obtained from the API call. A context string for the reply to the user speech input by the trained automatic agent may be constructed based on the utterance templates and the response of the API call.

Abstract: In one aspect, a playback device includes a voice assistant service (VAS) wake-word engine and a command keyword engine. The playback device detects, via the command keyword engine, a first command keyword, and determines whether one or more playback conditions corresponding to the first command keyword are satisfied. Based on (a) detecting the first command keyword and (b) determining that the one or more playback conditions corresponding to the first command keyword are satisfied, the playback device playback device performs a first playback command corresponding to the first command keyword. When the playback device detects, via the wake-word engine, a wake-word in voice input, the playback device streams sound data corresponding to at least a portion of the voice input to one or more remote servers associated with the VAS.

Abstract: An electronic device according to various embodiments may comprise a memory in which one or more applications are installed, a communication circuit, and a processor, wherein the processor is configured to acquire audio data during execution of a designated application among the one or more applications, wherein the acquiring of audio data comprises an operation of storing, in the memory, at least a portion including multiple pieces of phoneme information among the audio data, when a designated condition is satisfied, transmit the at least portion to an external electronic device so that the external electronic device generates designated information for execution of at least one application among the one or more applications by using at least a part of the multiple pieces of phoneme information stored before the designated condition is satisfied, and on the basis of the designated information, execute the at least one application in relation to the designated application.

Abstract: The invention relates to a method for an efficient dialogue configuration and interpretation in a computer-supported automated dialogue system. The invention offers, inter alia, the advantage that the work complexity when generating dialogues, and thus also the error propensity, is reduced. Furthermore, it is possible to take the context of sub-dialogs into consideration and dynamically generate a dialogue depending on said context. Furthermore, the method can automatically initiate a dialogue with a human user. The invention further relates to a correspondingly designed system assembly and to a computer program product with control commands which carry out the method or operate the system assembly.

Abstract: The present teaching relates to method, system, medium, and implementations for enabling communication with a user. Information representing surrounding of a user engaged in an on-going dialogue is received via the communication platform, wherein the information includes a current response from the user in the on-going dialogue and is acquired from a current scene in which the user is present and captures characteristics of the user and the current scene. Relevant features are extracted from the information. A state of the user is estimated based on the relevant features and a dialogue context surrounding the current scene is determined based on the relevant features. A feedback directed to the current response of the user is generated based on the state of the user and the dialogue context.

Abstract: Various embodiments of the disclosure disclose a method and apparatus for processing a voice recognition service in an electronic device. According to various embodiments of the disclosure, an electronic device may include a microphone, a memory, and a processor operatively coupled to the microphone and the memory. The processor may be configured to wake-up on the basis of detection of a wake-up word, process a first task corresponding to a first voice command of a user on the basis of the wake-up, set a wait time during which a follow-up command can be received on the basis of the processing of the first task, detect a second voice command of the user during the wait time, analyze a conversational context on the basis of the first voice command and second voice command, and process a second task on the basis of a result of the analysis. Various embodiments are possible.

Abstract: One embodiment provides a method that includes receiving adjusted labeled data based on emotional tone factors. Words are analyzed using a tone latent Dirichlet allocation (T-LDA) model that models tone intensity using the emotional tone factors and integrating the adjusted labeled data. Representative words are provided for each emotional tone factor based on using the T-LDA model. The representative words are obtained using the T-LDA model based on determining posterior probabilities and adjusting the posterior probabilities based on an auxiliary topic.

Abstract: Selectively performing voice recognition using one device among multiple devices that recognize and execute the voice recognition based on at least one of apparatus information of the multiple devices and a function parsed from a result of the voice recognition. Thereby, only a single preferable device in an environment in which multiple devices exist, which can service the user input via voice recognition, actually responds to the voice input and services the voice input of the user.