Abstract: In one aspect, a playback device includes at least one microphone configured to detect sound. The playback detects sound via the one or more microphones and determines whether (i) the detected sound includes a voice input, (ii) the detected sound excludes background speech, and (iii) the voice input includes a command keyword. In response to the determining, the playback device performs a playback function corresponding to the command keyword.

Abstract: A method includes receiving a spoken utterance that includes a plurality of words, and generating, using a neural network-based utterance classifier comprising a stack of multiple Long-Short Term Memory (LSTM) layers, a respective textual representation for each word of the of the plurality of words of the spoken utterance. The neural network-based utterance classifier trained on negative training examples of spoken utterances not directed toward an automated assistant server. The method further including determining, using the respective textual representation generated for each word of the plurality of words of the spoken utterance, that the spoken utterance is one of directed toward the automated assistant server or not directed toward the automated assistant server, and when the spoken utterance is directed toward the automated assistant server, generating instructions that cause the automated assistant server to generate a response to the spoken utterance.

Abstract: An information processor includes a generation section that generates a specified character string on the basis of at least one of voice information corresponding to a content of speech detected by a voice detection section and vehicle information acquired from a vehicle. With this configuration, a user can input the specified character string, which is a hashtag, without an operation. Thus, compared to the related art in which the hashtag is generated on the basis of the operation (manual input) by the user, a burden on the user can significantly be reduced, and an input error can be prevented.

Abstract: A method for a voice interaction is provided according to embodiments of the disclosure, the method belonging to the field of smart devices. The method may include: receiving an external input; checking a current time in response to the external input; calling a voice program; and raising a question according to the current time and the called voice program, and playing the called voice program. The method and apparatus for a voice interaction may perform more immersive interaction with a user, thereby improving the user experience.

Abstract: A voice interaction method and apparatus, a terminal, a server, and a readable storage medium are provided. The method includes the following steps: obtaining a user's demand according to the user's voice; determining a pre-stored task template matched with the user's demand; matching the user's demand with a necessary slot in the matched task template; and if the user's demand lacks content of the necessary slot, executing a step of obtaining the content of the necessary slot, to obtain the content of the necessary slot; wherein the task template is a template generated in advance according to information required for activating a task operation through voice, the slot is information in the task template, and the necessary slot is necessary information in the task template for activating the task operation.

Abstract: A method is provided for communicating a non-speech message as audio from a first device to a second device such that information can be passed between the first and second device. The method includes: encoding the non-speech message as a dissimilar speech message having a plurality of phonemes; transmitting the speech message over one or more audio communications channels from the first device; receiving the speech message at the second device; recognizing the speech message; and decoding the dissimilar speech message to the non-speech message. By using existing audio functionality, and the increasingly more reliable voice recognition applications, an improved method is provided for sharing complex data messages using commonly available communication channels.

Abstract: A local extremum calculator detects a local maximum sample and a local minimum sample of a digital audio signal. A number-of-sample detector detects a sample interval between the local maximum sample and the local minimum sample. A difference value calculator calculates difference values between adjacent samples. A correction value calculator calculates a first correction value by multiplying the difference value between the local maximum sample and a first adjacent sample by a coefficient and calculates a second correction value by multiplying the difference value between the local minimum sample and a second adjacent sample by the coefficient. When a periodic signal detector detects that the digital audio signal is a single sine wave, an adder/subtractor does not add the first correction value to the first adjacent sample, and does not subtract the second correction value from the second adjacent sample.

Abstract: Disclosed herein are system, method, and computer program product embodiments for a text-to-speech system. An embodiment operates by identifying a document including text, wherein the text includes both a structured portion of text, and an unstructured portion of text. Both the structured portion and unstructured portions of the text are identified within the document rich data, wherein the structured portion corresponds to a rich data portion that includes both a descriptor and content, and wherein an unstructured portion of the text includes alphanumeric text. A request to audibly output the document including the rich data portion is received from a user profile. A summary of the rich data portion is generated at level of detail corresponding to the user profile. The audible version of the document including both the alphanumeric text of the unstructured portion of the document and the generated summary is audibly output.

Abstract: Disclosed are an information providing device and an information providing method, which provide information enabling a conversation with a user by executing an artificial intelligence (AI) algorithm and/or a machine learning algorithm in a 5G environment connected for Internet-of-Things. An information providing method according to one embodiment of the present disclosure includes gathering first situational information from a home monitoring device, gathering, from the first electronic device, second situational information corresponding to the first situational information, gathering, from the home monitoring device, third situational information containing a behavioral change of the user after gathering the first situational information, generating a spoken sentence to provide to the user on the basis of the first situational information to the third situational information, and converting the spoken sentence to spoken utterance information to be output to the user.

Abstract: The main object of the present application is to provide a method and device for information interaction by quantitatively inputting voice indicators and processing and interacting information, the method comprising: displaying and persistently flashing a first prompt word and starting to receive a first input voice of a user; comparing the first input voice with the first prompt word; displaying and persistently flashing a second prompt word and starting to receive a second input voice of the user; comparing the second input voice with the second prompt word; and if the second input voice is matched with the second prompt word, then integrating the first input voice and the second input voice to be a digital voice file, and storing the digital voice file. The present application can help the user correctly, quickly and simply record sound, and reduce interference factors to the least, and can accurately, completely and conveniently acquire user sound, thus facilitating subsequent analysis and recognition.

Abstract: Provided are a method of associating an AI device with a device based on a behavior pattern of a user and a device therefor. The method of associating the AI device with the device according to an embodiment of the invention receives a preset behavior pattern of the user sensed by a first camera from the first camera, receives a voice command for controlling an operation of the device from the user, and transmits the voice command to the device, thus allowing devices having no AI function to be used in conjunction with the AI device. The AI device and the dive of the invention may be associated with artificial intelligence modules, drones (unmanned aerial vehicles (UAVs)), robots, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G service, etc.

Abstract: There is provided an information processing apparatus, an information processing method, and a program capable of providing a more convenient speech recognition service. The processing of recognizing, as an edited portion, a desired word configuring a sentence presented to a user as a speech recognition result, acquiring speech information repeatedly uttered for editing a word of the edited portion, and connecting speech information other than a repeated utterance to the speech information is performed, and speech information for speech recognition for editing is generated. Then, speech recognition is performed on the generated speech information for speech recognition for editing.

Abstract: Techniques for limiting natural language processing performed on input data are described. A system receives input data from a device. The input data corresponds to a command to be executed by the system. The system determines applications likely configured to execute the command. The system performs named entity recognition and intent classification with respect to only the applications likely configured to execute the command.

Abstract: A method for a virtual assistant is provided. The method includes controlling, in a first operation mode, at least one sensor to sense a physical quantity. Further, the method includes receiving, in the first operation mode, sensor data indicative of the physical quantity from the at least one sensor. Additionally, the method includes processing, in the first operation mode, the sensor data to detect whether the sensor data exhibit a predetermined characteristic. If the predetermined characteristic is detected in the sensor data, the method includes setting the operation mode of the virtual assistant to a second operation mode assigned to the predetermined characteristic.

Abstract: An audio firewall system has a microphone that generates audio data. A speech-to-text engine converts the audio data to text data. The text data is parsed for a service wake word and corresponding content data. The service wake word identifies one of a local security system and a remote assistant server. A text-to-speech engine converts the service wake word and the corresponding content data to converted audio data. The converted audio data is provided to the remote assistant server. The content data is provided to the local security system. The audio firewall system receives a response from the remote assistant server or the local security system and outputs an audio signal corresponding to the response.

Abstract: Examples for augmenting user recognition via speech are provided. One example method comprises, on a computing device, monitoring a use environment via one or more sensors including an acoustic sensor, detecting utterance of a key phrase via data from the acoustic sensor, and based upon the selected data from the acoustic sensor and also on other environmental sensor data collected at different times than the selected data from the acoustic sensor, determining a probability that the key phrase was spoken by an identified user. The method further includes, if the probability meets or exceeds a threshold probability, then performing an action on the computing device.

Abstract: Implemented are an apparatus and a method that enable highly accurate intent estimation of a user utterance. An utterance learning adaptive processing unit analyzes a plurality of user utterances input from a user, generates learning data in which entity information included in a user utterance with an unclear intent is associated with a correct intent, and stores the generated learning data is a storage unit. The utterance learning adaptive processing unit generates learning data in which an intent, acquired from a response utterance from the user to an apparatus utterance after input of a first user utterance with an unclear intent, is recorded in association with entity information included in the first user utterance. The learning data is recorded to include superordinate semantic concept information of the entity information. At the time of estimating an intent for a new user utterance, learning data with similar superordinate semantic concept information is used.

Abstract: Systems and methods of machine learning for digital assets and message creation are provided herein. The present disclosure includes mechanisms for receiving one or more assets that include textual content, performing machine learning on the one or more assets in order to determine relevant words, phrases, and statistics included in the textual content, and displaying segments of data on a graphical user interface that also includes an interface that is used to create a message using content of the segments of the textual content that have been extracted from the one or more assets.

Abstract: A portable terminal includes: a storage part which holds work information in which a plurality of items included in work are associated with respective work results; a speech recognition part which stores a work result(s) obtained by recognizing an utterance(s) of a worker in the storage part; and a communication part which transmits, when the speech recognition part recognizes a predetermined utterance(s) of a worker, a work result(s) held by the storage part to a management server or another (other) portable terminal(s). When the communication part receives a work result(s) from the management server or another (other) portable terminal(s), the communication part stores the received work result(s) in the storage part.

Abstract: A system for operating an automobile comprising a transponder having a user interface to receive commands from a user and operating as a virtual assistant, wherein the commands comprise commands for operation of a door of the automobile and a microprocessor in the automobile responsive to the transponder. The system for operating an automobile further comprising a detector subsystem configured to determine a potential strike of an object based on a determined distance to the object, wherein the microprocessor receives a communication from the transponder and wherein the automobile is configured to send a command to a door of the automobile in response to the communication. Further, the system in the automobile is configured to avoid the potential strike determined by the detector system by limiting the operation of the door and producing an alert to a user as to the potential strike.