Abstract: As noted above, example techniques relate to offline voice control. A local voice input engine may process voice inputs locally when processing voice inputs via a cloud-based voice assistant service is not possible. Some techniques involve local (on-device) voice-assisted set-up of a cloud-based voice assistant service. Further example techniques involve local voice-assisted troubleshooting the cloud-based voice assistant service. Other techniques relate to interactions between local and cloud-based processing of voice inputs on a device that supports both local and cloud-based processing.

Abstract: An operation terminal includes: an imaging part configured to image a space; a human detecting part configured to detect a user based on information on the space imaged; a voice inputting part configured to receive inputting of the spoken voice of the user; a coordinates detecting part configured to detect a first coordinate of a predetermined first part of an upper limb of the user and a second coordinate of a predetermined second part of an upper half body excluding the upper limb of the user based on information acquired by a predetermined unit when the user is detected by the human detecting part; and a condition determining part configured to compare a positional relationship between the first coordinate and the second coordinate, and configured to bring the voice inputting part into a voice inputting receivable state when the positional relationship satisfies a predetermined first condition at least one time.

Abstract: Systems and methods for recognizing and executing spoken commands using speech recognition. Exemplary implementations may: store actionable phrases; obtain audio information representing sound captured by a mobile client computing platform associated with a user; detect any spoken instances of a predetermined keyword present in the sound represented by the audio information; perform speech recognition on the sound represented by the audio information; identify an utterance of an individual actionable phrase in speech temporally adjacent to the spoken instance of the predetermined keyword that is present in the sound represented by the audio information; perform natural language processing to identify an individual command uttered temporally adjacent to the spoken instance of the predetermined keyword that is present in the sound represented by the audio information; and effectuate performance of instructions corresponding to the command.

Abstract: The present disclosure provides a content recognizing method and apparatus, a device and a computer storage medium, wherein the method comprises: a smart multimedia device performing speech recognition and intention parsing for a speech instruction; if a content recognition intention is obtained from the parsing, internally recording multimedia content that is being played by the smart multimedia device; sending internally-recorded media data to a server side, and obtaining a content recognition result returned by the server side for the media data. The user may implement recognition of multimedia content through speech interaction with the smart multimedia device, and operations are simple without depending on other smart devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing voice data are provided. One of methods, implemented by an IoT device, includes: receiving voice data from a server, wherein the voice data is obtained through converting text data to voice data by the server; determining a content attribute associated with the voice data; determining a content attribute type of the content attribute associated with the voice data; determining a first play rule matching the content attribute type based on a matching relationship between content attribute types and respective first play rules, wherein the first play rule including a play starting time and a play mode; and automatically playing the voice data according to the play starting time and the play mode.

Abstract: In a voice controlled system, multiple applications are configured to respond to various commands. The voice controlled system includes client devices and servers. The correct application to receive a natural language command is identified based on how well the command matches functions of the application. A target application to receive the command may additionally be selected based on which application is most likely to receive a command. Likelihood of an application receiving a command may be determined by considering context. The command may be a voice input to a client device that is analyzed by speech recognition technology to determine word strings representing possible commands. Thus, the selection of a target application to receive the command may be based on word strings from the natural language input, a closeness of fit between the command and an application, and/or the likelihood an application is the target for the next incoming command.

Abstract: A method comprises determining a first modification weight according to linear spectral frequency (LSF) differences of the current frame and LSF differences of a previous frame of the current frame, when a signal characteristic of the current frame meets a preset modification condition, modifying the linear predictive parameter of the current frame according to the determined first modification weight, and coding the current frame according to the modified linear predictive parameter.

Abstract: A media drive 32 is loaded with a data disc 44b in which a plurality of files composing application software is recorded. A language information holding section 110 holds use language information configured to specify a use language selected by a user in the information processing apparatus 10 concerned. For causing application to be in an executable state, a recording processing section 104 copies a language-dependent file recorded in the data disc 44b to an auxiliary storage apparatus 2 on the basis of the use language information held in the language information holding section 110.

Abstract: A conversational bot system uses a set of conversations that have been annotated to identify speech acts, wherein a speech act is a labeled grouping of utterances. To facilitate processing, a data model associated with a multi-turn conversation is received. The data model comprises an observation history. Upon receipt of query that includes a sequence of at least two or more utterances, an utterance ranking algorithm is applied. The algorithm selectively reorders the utterances in the sequence into a ranked order of importance that reflects a lowest to highest priority of response. In response to applying the utterance ranking algorithm, the data model is then updated to reflect the ranked order. In one embodiment, updating the data model positions the highest priority utterance as a most recent utterance in the observation history. The updated data model is then used to attempt to generate a coherent response to the query.

Abstract: An electronic device includes an audio input module, a memory storing a speech recognition application, a first application, and a second application, a communication circuit communicating with a first NLU server associated with the first application and a second NLU server associated with the second application, and a processor electrically connected to the audio input module, the memory, and the communication circuit and executing the speech recognition application.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

Abstract: This disclosure is directed to systems, methods, and devices related to providing the execution of multi-operation sequences based on a trigger occurring which may be a voice-controlled utterance or execution may be based on a trigger occurring and a condition occurring. In accordance with various principles disclosed herein, multi-operation sequences may be executed based on voice-controlled commands and the identification that a trigger has occurred. The voice-controlled electronic devices can be configured to communicate with, and to directly control the operation of, a wide array of other devices. These devices can include, without limitation, outlets that can be turned ON and OFF remotely such that anything plugged into them can be controlled, turning lights ON and OFF, setting the temperature of a network accessible thermostat, etc.

Abstract: There is provided an information processing device including an analysis unit configured to analyze a character string indicating contents of utterance obtained as a result of speech recognition, and a display control unit configured to display the character string indicating the contents of the utterance and an analysis result on a display screen.

Abstract: A computer system is provided that automatically generates a natural language processing model from a provided API specification. Intent names are based on operation type and name. Entity datasets are constructed based on the generated intent name. A plurality of training phrases are generated based on the entity dataset and an action dataset with a name and corresponding parameters is generated.

Abstract: In one embodiment, a method includes, by one or more computing systems, receiving a user input comprising a plurality of n-grams from a user of a client system, generating a tree-structured representation for the user input based on a parsing by a compositional model, resolving the tree-structured representation by applying a depth-first search algorithm, wherein the tree-structured representation comprises one or more non-resolvable non-terminal nodes associated with one or more slots, and wherein each non-terminal parent node of a non-resolvable non-terminal node is partially resolved based on partial slot information associated with the non-resolvable non-terminal node, and wherein each non-resolvable non-terminal node is resolved based on the respective partially resolved non-terminal parent node of the non-resolvable non-terminal node, generating a response to the user input based on the resolved tree-structured representation, sending instructions for presenting the response to the client system of the

Abstract: To provide a speech recognition results re-ranking technology for re-ranking speech recognition results so as to render speech recognition results suitable for intended use of speech recognition while reducing preparation costs required prior to execution of re-ranking processing of speech recognition results. A speech recognition results re-ranking device includes: a speech recognition unit 210 that generates a speech recognition result set with recognition score from speech data; and a re-ranking unit 220 that generates a speech recognition result set with integrated score from the speech recognition result set with recognition score by using a word vector expression database, a cluster center vector expression database, and a normalized knowledge information word DF value database.

Abstract: A method for natural language query processing in an internet of things (IoT) system and an electronic device thereof are provided. The method includes receiving a natural language query including a plurality of attributes. Further, the method includes determining, by the IoT query engine, things from a plurality of things to be queried from a unified metadata based on the plurality of attributes. The unified metadata includes information about the plurality of things connected in the IoT system. Further, the method includes sending, by the IoT query engine, at least one structural query to each of the determined things. The at least one structural query is generated based on the plurality of attributes and the determined things. Further, the method includes retrieving, by the IoT query engine, results from each of the determined things.

Abstract: This patent application is directed to interaction between a voice-controlled device and a language processing system that processes user requests. The requests can be requests for information or they can be requests to control a device, such as “Turn on the bedroom light.” The disclosure includes various embodiments for trying to resolve system errors in a manner that provides an improved customer experience. The improvements described include the capability of the overall system to recognize that an error has occurred while attempting to fulfill a request that was submitted as part of a recognized spoken utterance. Instead of simply doing nothing, or of playing a message to the customer to try again later, the system would now let the user know it was still processing the request while making another attempt at fulfilling the request.

Abstract: A method, a computer system, and a computer program product for detecting voice commands. Audio is recorded by the computer system to form a recorded audio. The computer system then determines whether a voice command spoken by a first person is present in the recorded audio. If the voice command is present in the recorded audio, the computer system determines whether the voice command is directed to a second person by the first person. If the voice command is not being directed to the second person, the computer system processes the voice command, wherein processing of the voice command occurs without a wake word.

Abstract: According to one embodiment, a word detection system acquires speech data including a plurality of frames, generates the speech characteristic amount, calculates a frame score by matching a reference model based on the speech characteristic amount associated with a target word with the frames in the speech data, calculates a first score of the word from the frame score, detects the word from the speech data based on the first score, calculates a second score of the word based on time information on the start and the end of the detected word and the frame score, compares the value of the second score with the second scores of a plurality of words, and determines a word to be output based on the comparison result.