Abstract: The present subject matter at least describes a method and a system (300, 1200) of performing speech-recognition in an electronic device having an embedded speech recognizer. The method comprises receiving an input-audio comprising speech at a device. In real-time, at-least one speech-recognition module is selected within at least one of the device and a server for recognition of at least a portion of the received speech based on a criteria defined in terms of a) past-performance of speech-recognition modules within the device and server; b) an orator of speech; and c) a quality of service associated with at least one of the device and a networking environment thereof. Based upon the selection of the server, output of the selected speech-recognition modules within the device are selected for processing by corresponding speech-recognition modules of the server. An uttered-speech is determined within the input-audio based on output of the selected speech-recognition modules of the device or the server.

Abstract: Provided is an information processing device including a response control unit that controls a response to a user's utterance based on a first utterance interpretation result and a second utterance interpretation result. The first utterance interpretation result is a result of natural language understanding processing for an utterance text generated by automatic speech recognition processing based on the user's utterance and the second utterance interpretation result is an interpretation result acquired based on learning data in which the first utterance interpretation result and the utterance text used to acquire the first utterance interpretation result are associated with each other. The response control unit further controls the response to the user's utterance based on the second utterance interpretation result in a case where the second utterance interpretation result is acquired based on the user's utterance before acquisition of the first utterance interpretation result.

Abstract: A speech decoding method is performed by a computer device, the speech including a current audio frame and a previous audio frame. The method includes: obtaining a target token corresponding to a smallest decoding score from a first token list including first tokens obtained by decoding the previous audio frame, each first token including a state pair and a decoding score, the state pair being used for characterizing a correspondence between a first state of the first token in a first decoding network corresponding to a low-order language model and a second state of the first token in a second decoding network corresponding to a differential language model; determining pruning parameters according to the target token and an acoustic vector of the current audio frame when the current audio frame is decoded; and decoding the current audio frame according to the first token list, the pruning parameters, and the acoustic vector.

Abstract: A voice support server is used to provide voice control functionality to a third party application that does not natively support voice control functions. The voice support server implements a domain specific to the third party application that maintains a domain-specific language model (DLM) reflecting the functionality of the third party application. The DLM comprises a plurality of intent patterns corresponding to different commands and their possible variations that may be issued by the user, and maps each intent pattern to a corresponding action to be performed by the third party application. Received audio data is analyzed to determine one or more user utterances, which are transcribed and compared to the intent patterns of the DLM to identify an intent corresponding to the user utterance. The voice control module may then transmit instructions to the third party application to perform the action corresponding to the identified intent.

Abstract: Examples described herein include systems and methods for brokerless reliable totally ordered many-to-many inter-process communication on a single node. A messaging protocol is provided that utilizes shared memory for one of the control plane and data plane, and multicast for the other plane. Readers and writers can store either control messages or message data in the shared memory, including in a ring buffer. Write access to portions of the shared memory can be controlled by a robust futex, which includes a locking mechanism that is crash recoverable. In general, the writers and readers can control the pace of communications and the crash of any process does not crash the overall messaging on the node.

Abstract: An electronic device includes memory circuitry, interface circuitry, and processor circuitry. The processor circuitry is configured to transmit, to a plurality of electronic reference devices, a first signal, the first signal having a pulse width below a threshold. The processor circuitry is configured to determine, based on the received second signals and at least one predetermined time period, a time of flight of each of the second signals. The processor circuitry is configured to obtain, from the memory circuitry, reference positions of the plurality of electronic reference devices. The processor circuitry is configured to determine, based on the associations, one or more candidate positions of the electronic device. The processor circuitry is configured to determine, based on the distances, the one or more candidate positions, and the obtained reference positions, a position of the electronic device.

Abstract: Techniques for partially processing an input on a device and completing processing at a remote system are provided. The device may process an input using an on-device machine learning (ML) model, and determine to cease processing at an intermediary node of the (ML) model based on the output of the intermediary node. Based on the output of the intermediary node satisfying a condition, the device may use the output of the intermediary node to generate an output responsive to the input. Conversely, if the output of the intermediary node does not satisfy a condition, the device may send the output of the intermediary node to the remote system, so the remote system can use another machine learning model to complete processing with respect to the input.

Abstract: Example techniques involve invoking voice assistance for a media playback system. In some embodiments, a NMD stores in memory a set of command information comprising a listing of playback commands and associated command criteria. The NMD captures a voice input and detects inclusion, within the voice input, of one or more particular playback commands from among the playback commands in the listing. In response, the NMD selects a local voice assistant that supports (a) one or more additional playback commands relative to a cloud-based VAS and (b) fewer non-playback commands relative to the cloud-based VAS, determines, via the local voice assistant, an intent in the captured voice input, and performs a response to the determined intent. The NMD foregoes selection of the cloud-based VAS when the local voice assistant is selected.

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: Speech processing tasks may be allocated at least partly to a local device (e.g., user computing device that receives spoken words) and at least partly to a remote device to determine one or more user commands or tasks to be performed by the local device. The remote device may be used to process speech that the local device could not process or understand, or for other reasons, such as for error checking. The local device may then execute or begin to execute locally determined tasks to reduce user-perceived latency. Meanwhile, the entire media input, or a portion thereof, may be sent to the remote device to process speech, verify the tasks and/or identify other user commands in the media input (or portion thereof).

Abstract: Disclosed is the technology for computer-based “Daily Brief” service, which includes methods and corresponding systems for proactively providing push notifications for users of chat information systems. The push notifications are dynamically generated and presented to the user based on identification of one or more triggering events, which may include predetermined time/date, current geographical location, activity of peers and friends in social media associated with the user, scheduled events, appointments, meetings, emails, instant messages, and many more. The described technology improves the interaction interface between the user and chat information system.

Abstract: Disambiguating question answering responses by receiving voice command data associated with a first user, determining a first user identity according to the first user voice command data, determining a first user activity context according to the first user voice command data, determining a first response for the first user, receiving voice command data associated with a second user, determining a second user identity according to the second user voice command data, determining a second user activity context according to the second user voice command data, determining a second response for the second user, determining a predicted ambiguity between the first response and the second response, altering the first response according to the predicted ambiguity, and providing the first response and the second response.

Abstract: Embodiments of the invention are directed to techniques that include receiving a query intended for a targeted database and determining that the query is from an unauthorized user. A response is returned to the unauthorized user generated by a model, the response being dynamically generated to fulfill the query. The model is configured to generate responses consistent with any previous responses returned to the unauthorized user.

Abstract: Examples described herein include systems and methods for brokerless reliable totally ordered many-to-many inter-process communication on a single node. A messaging protocol is provided that utilizes shared memory for one of the control plane and data plane, and multicast for the other plane. Readers and writers can store either control messages or message data in the shared memory, including in a ring buffer. Write access to portions of the shared memory can be controlled by a robust futex, which includes a locking mechanism that is crash recoverable. In general, the writers and readers can control the pace of communications and the crash of any process does not crash the overall messaging on the node.

Abstract: A voice processing method is disclosed. The voice processing method applies first and second sentence vectors extracted from first and second utterances, that are included in one dialog group and are separated from each other, to a learning model and generates an output from which at least one word having an overlapping meaning is removed. The voice processing method can be associated with an artificial intelligence module, an unmanned aerial vehicle (UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.

Abstract: A system may include first and second speech-processing systems. The first speech-processing system may process received audio data and determine that a command represented therein is associated with a second speech-processing system. The first speech-processing system may send command data to the second speech-processing system and receive response data in return. The first speech-processing system may then process the response data to determine second response data that includes an indication of the second speech-processing system and cause output of audio corresponding to the second response data.

Abstract: A system and method for updating computerized language models is provided that automatically adds or deletes terms from the language model to capture trending events or products, while maximizing computer efficiencies by deleting terms that are no longer trending and use of knowledge bases, machine learning model training and evaluation corpora, analysis tools and databases.

Abstract: Systems, methods, and apparatuses for implementing a geo-demographic zoning optimization engine are disclosed.

Abstract: To simplify assisting a user in their day-to-day activities, a communication for performing an action may be sent to a user in the form of a query, where the query includes the most likely set of choices for the action arranged in a group of dichotomous (e.g., yes/no) or multiple choice answers. In this manner, a user may respond to the query by simply selecting one of the dichotomous or multiple choice answers. Historical logs of past actions, responses, queries, and so forth, may be used to predict future user actions or needs, and to formulate future queries for sending to the user. These techniques may be implemented, for example, through a remote coordination server or directly through a user's personal electronics device.

Abstract: The present invention provides a caption service system for remote speech recognition, which provides caption service for the hearing impaired. This system includes a speaker and a live broadcast equipment at A, a listener-typist and a computer at B, a hearing impaired and a live screen at C, and an automatic speech recognition (ASR) caption server at D. Connect the live broadcast equipment, the computer, the live screen and the ASR caption server with a network. The speaker's audio is sent to the automatic speech recognition (ASR) caption server to be converted into text, which is corrected by the listener-typist, and then the text caption is sent to the live screen of the hearing impaired together with the speaker's video and audio, so that the hearing impaired can see the text caption spoken by the speaker.

Abstract: A communication device and method can include one or more processors operatively coupled to memory, a sensor and an output device, where the one or more processors to perform operations of identifying target person locations using internet searching and short range communication enabled devices such as Bluetooth LE devices.

Abstract: Some speech processing systems may handle some commands on-device rather than sending the audio data to a second device or system for processing. The first device may have limited speech processing capabilities sufficient for handling common language and/or commands, while the second device (e.g., an edge device and/or a remote system) may call on additional language models, entity libraries, skill components, etc. to perform additional tasks. An intermediate data generator may facilitate dividing speech processing operations between devices by generating a stream of data that includes a first-pass ASR output (e.g., a word or sub-word lattice) and other characteristics of the audio data such as whisper detection, speaker identification, media signatures, etc. The second device can perform the additional processing using the data stream; e.g., without using the audio data. Thus, privacy may be enhanced by processing the audio data locally without sending it to other devices/systems.

Abstract: A method may include obtaining audio data originating at a first device during a communication session between the first device and a second device and providing the audio data to a first speech recognition system to generate a first transcript based on the audio data and directing the first transcript to the second device. The method may also include in response to obtaining a quality indication regarding a quality of the first transcript, multiplexing the audio data to provide the audio data to a second speech recognition system to generate a second transcript based on the audio data while continuing to provide the audio data to the first speech recognition system and direct the first transcript to the second device, and in response to obtaining a transfer indication that occurs after multiplexing of the audio data, directing the second transcript to the second device instead of the first transcript.

Abstract: A device to process speech includes a speech processing network that includes an input configured to receive audio data corresponding to audio captured by one or more microphones. The speech processing network also includes one or more network layers configured to process the audio data to generate a network output. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the network output to be provided as a common input to each of the multiple speech application modules. A first speech application module corresponds to a speaker verifier, and a second speech application module corresponds to a speech recognition network.

Abstract: A computer program and the like are provided that are capable of causing an information processing device connected to a private network, to automatically execute operation processing of a browser. The computer program is a computer program for causing the information processing device connected to the private network, to automatically execute the operation of the browser that accesses a web server on the private network, based on an instruction from a server connected to a global network, and causes the information processing device to execute the processing of: requesting the server to establish a connection; obtaining an operation instruction related to the operation processing which is push-transmitted from the server, by using the connection; executing the operation processing of the browser based on the obtained operation instruction; obtaining an execution result of the operation processing; and outputting the obtained execution result to the server.

Abstract: The present disclosure is generally directed to a data processing system for customizing content in a voice activated computer network environment. With user consent, the data processing system can improve the efficiency and effectiveness of auditory data packet transmission over one or more computer networks by, for example, increasing the accuracy of the voice identification process used in the generation of customized content. The present solution can make accurate identifications while generating fewer audio identification models, which are computationally intensive to generate.

Abstract: A method for providing responsive actions to user inputs in a multi-domain context includes receiving, by a speech-based user interface, a first speech input from a user and converting said first speech input into a text-based representation of the first speech input. A natural language processor processes the text-based representation to determine an intent, entity and internal state of the first speech input. The method further includes determining, by a model-based module based on the intent, entity and internal state, a first data processing policy to apply to the first speech input, wherein the first data processing policy is either a rules-based data processing policy applied by a rules-based module or a statistical model-based data processing policy applied by the model-based module. The first responsive action is generated by the determined first data processing module, and outputted via the speech-based user interface and/or a machine interface.

Abstract: A method is provided for generating a classification model configured to select an optimal execution combination for query processing. The method provides, to a processor, training queries and different execution combinations for executing the training queries. Each different execution combination involves a respective different query engine and a respective different runtime. The method extracts, from a set of Directed Acyclic Graphs (DAGs) using a set of Cost-Based Optimizers (CBOs), a set of feature vectors for each of the plurality of training queries. The method adds, by the processor to each of merged feature vectors a respective label indicative of the optimal execution combination based on actual respective execution times of the plurality of different execution combinations, to obtain a set of labels. The method trains, by the processor, the classification model by learning the set of merged feature vectors with the set of labels.

Abstract: Systems and methods for distributed voice processing are disclosed herein. In one example, the method includes detecting sound via a microphone array of a first playback device and analyzing, via a first wake-word engine of the first playback device, the detected sound. The first playback device may transmit data associated with the detected sound to a second playback device over a local area network. A second wake-word engine of the second playback device may analyze the transmitted data associated with the detected sound. The method may further include identifying that the detected sound contains either a first wake word or a second wake word based on the analysis via the first and second wake-word engines, respectively. Based on the identification, sound data corresponding to the detected sound may be transmitted over a wide area network to a remote computing device associated with a particular voice assistant service.

Abstract: Systems and methods are described herein for interpreting natural language search queries that account for contextual relevance of words of the search query that would ordinarily not be processed, including, for example, processing each word of the query. Each term is associated with a respective part of speech, and a frequency of occurrence of each term in content metadata is determined. A relevance of each term is then determined based on its respective part of speech and frequency. The natural language search query is then interpreted based on the importance or relevance of each term.

Abstract: A moving object control system includes a server, a portable terminal configured to transmit authentication information issued by the server, and a controller provided in a moving object and configured to authenticate the portable terminal according to the authentication information transmitted from the portable terminal, and when the portable terminal is authenticated, control the moving object in response to an operation signal from the portable terminal. The controller is configured to perform information communication with the server and control the moving object according to control information received from the server.

Abstract: An electronic apparatus includes: at least one processor configured to: receive audio of a voice input of a user; obtain, from a plurality of voice recognizers capable of recognizing the voice input, a plurality of recognition results of the received audio; and perform an operation based on a recognition result of which recognition suitability for the voice input is identified to be high, among the plurality of recognition results.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for transferring dialog sessions between devices using deep links. The dialog sessions can correspond to interactions, mediated by an automated assistant, between a user and a third party application. During the dialog session, a user can request that the dialog session be transferred to a different device, for example, to interact with the third party application through a different modality. In response, the automated assistant and/or the third party application can generate a link that can be transferred to the transferee device to allow the transferee device to seamlessly take over the dialog session. In this way, computational resources and electrical power can be preserved by not requiring a recipient device to re-process natural language inputs previously provided during the dialog session.

Abstract: Disclosed is an electronic apparatus capable of controlling voice recognition. The electronic apparatus increases a score of a category corresponding to a word included in user's utterance in a database when the instruction included in the user's utterance is present in the database. The electronic apparatus checks whether the score of the category corresponding to the word is equal to or greater than a preset value when the instruction is not present in the database. The electronic apparatus registers the instruction in the database so that the instruction is included in the category corresponding to the word when the score is equal to or greater than the preset value as the check result.

Abstract: A terminal device is provided and includes a communication interface including circuitry, a display and at least one processor configured to control the communication interface to transmit a user voice including a plurality of intents to an external server, based on word use information included in the user voice and summary information regarding the user voice generated based on user-related information being received from the external server, control the display to display the received summary information, based on a user feedback regarding the summary information being input, transmit information regarding the user feedback to the external server, and based on response information regarding the user voice generated based on the user feedback being received from the external server, control the display to provide the response information.

Abstract: Techniques for voice control of a patient care device are described. A patient care device receives an audio request from a user. The patient care device records the audio request. The patient care device transmits the audio request over a communication network to a speech recognition service, and in response receives, from the speech recognition service, a textual representation of the audio request. The patient care device matches the textual representation, using the computer processor, to a first command in a vocabulary of available commands, and in response performs the first command.

Abstract: Disclosed are an automatic question answering method and apparatus, a storage medium, and a server. The method includes: acquiring numerical features of a sentence to be queried; querying a target sentence in a question database according to the numerical features of the sentence to be queried, the question database including a plurality of sentences and answers corresponding to the plurality of sentences; and determining a target answer according to an answer corresponding to the target sentence. In this method, the sentence is represented by the numerical features, such that it is convenient to search questions similar to a question of a user in the question database, thereby achieving an effect of improving a search speed of the question.

Abstract: A system for classification of a customer query is disclosed. The system includes a customer interaction subsystem to receive the customer query from a customer, and a tokenizer subsystem to split the customer query into tokens. The system also includes a multitask profiler subsystem including a mapping module to map the tokens with pre-trained embedding data to assign mathematical codes to the tokens, an attention module to apply attention models hierarchically on a contextual embedding layer to obtain contextual mathematical codes corresponding to the tokens based on the mathematical codes, a classification module to classify the multiple tokens into profiles based on the contextual mathematical codes, and a profile generator to generate a human readable profile and a machine-readable profile based on the profiles. The machine-readable profile and the human readable profile includes at least one of a customer profile, a product profile, an issue profile or a combination thereof.

Abstract: A vehicle device includes: a communication device configured to transmit or receive a signal to or from a cloud server operating in conjunction with a service device of a parking lot upon entering the parking lot; and a controller configured to output parking lot information received from the cloud server upon entering the parking lot, and to identify charge settlement information of the parking lot from the cloud server to pay a settlement charge, when a predetermined charge settlement event occurs.

Abstract: Disclosed herein is a speech recognition method in a distributed network environment. A method of performing a speech recognition operation in an edge computing device includes receiving a natural language understanding (NLU) model from the cloud server, storing the received NLU model, receiving voice data spoken by a user from the client device, performing a natural language processing operation on the received voice data using the NLU model, performing speech recognition according to the natural language processing operation, and transmitting a result of the speech recognition to the client device. At least one of the edge computing device, a voice recognition device, and a server may be associated with an artificial intelligence module, a drone (an unmanned aerial vehicle (UAV)), a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.

Abstract: A universal data management interface (UDMI) system includes a processing system generates a visual interface through which a user can access, manage, and manipulate data on plural different types of remote databases. The UDMI connects to multiple standard database management systems and to allow multiple users to access, manage, and manipulate data within each of the multiple standard database management systems. The UDMI also allows multiple virtual databases that reside in a single database to be available as a network service.

Abstract: Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture.

Abstract: Systems and methods are described for a speech system that manages multiple grammars from one or more speech-enabled applications. The speech system includes a speech server that supports different grammars and different types of grammars by exposing several methods to the speech-enabled applications. The speech server supports static grammars that do not change and dynamic grammars that may change after a commit. The speech server provides persistence by supporting persistent grammars that enable a user to issue a command to an application even when the application is not loaded. In such a circumstance, the application is automatically launched and the command is processed. The speech server may enable or disable a grammar in order to limit confusion between grammars. Global and yielding grammars are also supported by the speech server. Global grammars are always active (e.g., “call 9-1-1”) while yielding grammars may be deactivated when an interaction whose grammar requires priority is active.

Abstract: Adjusting model parameters is described for a speech recognition system that combines recognition outputs from multiple speech recognition processes. Discriminative adjustments are made to model parameters of at least one acoustic model based on a joint discriminative criterion over multiple complementary acoustic models to lower recognition word error rate in the system.

Abstract: A speech recognition method comprises model selection step which selects a recognition model based on characteristic information of input speech and speech recognition step which translates input speech into text data based on the selected recognition model.

Abstract: Speech signal information is formatted, processed and transported in accordance with a format adapted for TCP/IP protocols used on the Internet and other communications networks. NULL characters are used for indicating the end of a voice segment. The method is useful for distributed speech recognition systems such as a client-server system, typically implemented on an intranet or over the Internet based on user queries at his/her computer, a PDA, or a workstation using a speech input interface.

Abstract: A speech recognition device that is capable of presenting, to a user in an easy-to-understand manner, whether or not the user's utterance is a word unregistered in a speech recognition dictionary and whether or not the utterance should be repeated due to a recognition error includes: a speech recognition vocabulary storage unit (102) which defines vocabulary for speech recognition; a speech recognition unit (101) which checks the uttered speech against the registered words; a reference similarity calculation unit (103) which calculates a similarity between the uttered speech and a combination of acoustic units, which are subwords; an unregistered word judgment unit (104) which judges, based on the result of the check by the speech recognition unit (101) and a result of the calculation performed by the reference similarity calculation unit (103), whether the uttered speech is a registered word or an unregistered word; an unregistered word storage (106) which stores unregistered words; an unregistered word cand

Abstract: The present invention can include a speech enrollment system including an ordered stack of grammars and a recognition engine. The ordered stack of grammars can include an application grammars layer, a confusable grammar layer, a personal grammar layer, a phrase enrolled grammar layer, and an enrollment grammar layer. The recognition engine can return recognition results for speech input by processing the input using the ordered stack of grammars. The processing can occur from the topmost layer in the stack to the bottommost layer in the stack. Each layer in the stack can includes exit criteria based upon a defined condition. When the exit criteria is satisfied, a result can be returned based upon that layer and lower layers of the ordered stack can be ignored.

Abstract: A system and method for improving voice recognition processing at a server system that receives voice input from a remotely located user system. The user system includes a microphone, a processor that performs front-end voice recognition processing of the received user voice input, and a communication component configured to send the front-end processed user voice input to a destination wirelessly over a network. The server system includes a communication component configured to receive the sent front-end processed user voice input, and a processor configured to complete voice recognition processing of the sent front-end processed user voice input.

Abstract: Disclosed is a method for controlling a cordless telephone device for use in a system that allows remote control of a home electric appliance. The method includes a first generation step of causing a first generation unit in a handset to encode audio input via a sound receiving unit in the handset to generate a first stream, and a first transmission step of transmitting the first stream to a base unit. The first generation step includes causing the first generation unit to generate instruction bit information and a first instruction stream when a first trigger indicating a request to start the remote control is given to the first generation unit. The first transmission step includes transmitting the instruction bit information and the first instruction stream to the base unit through a multiplexing scheme that is common to transmission of a first stream generated when the first trigger is not given.