Abstract: A barrier-free intelligent voice system and a method for controlling thereof, wherein multiple words are recognized from a voice audio to create multiple independent semantic units. Meanwhile, the system can continuously determine whether they are one of multiple voice tags created by the user. Thereafter, a target object, a program command, and a remark corresponding to the voice tag can be determined based on the successfully compared voice tag combination. Accordingly, a corresponding program can be started or a remote device can be triggered to operate. The present disclosure can be regarded as an AI intelligent voice processing engine. By allowing users to define different types of voice tag combinations, it can eliminate the grammatical and semantic analysis of natural language processing, eliminate speech translation differences and errors between different languages, effectively reduce the amount of calculations, increase the processing speed of the system, minimize system judgment errors.

Abstract: Techniques for generating a skill using skill portion deviceskill portion devices are described. A user generates a skill by connecting skill portion deviceskill portion devices in a particular manner. As devices are connected, a speech controllable device or a distributed system may maintain a data structure representing a skill configuration corresponding to the presently connected devices.

Abstract: An electronic device is provided and includes a display; a wireless communication circuit; a processor operatively connected to the display and the wireless communication circuit; and a memory operatively connected to the processor. The memory may store instructions that, when executed, cause the processor to obtain a command generated by an utterance input on an external device, and first data related to a function to be executed when the command is input on the external device by using the wireless communication circuit; obtain second data related to a function to be executed when the command is input on the electronic device; and determine whether the command is executable on the electronic device based on a result of a comparison between the first data and the second data.

Abstract: A multi-assistant controller includes an audio recorder and a detector. The audio recorder is configured to receive a sampled audio from a microphone, store the sampled audio in a circular buffer, and transfer the sampled audio from the circular buffer to a particular voice-activated assistant. The detector is configured to store multiple wake-up phrases that are recognizable by multiple voice-activated assistants, search the sampled audio to determine multiple probabilities that the sampled audio includes the wake-up phrases, select a particular wake-up phrase that has a highest probability among the probabilities, and send a callback to the particular voice-activated assistant that the particular wake-up phrase has been detected. The sampled audio that is transferred to the particular voice-activated assistant includes the particular wake-up phrase that was detected.

Abstract: Techniques for training a first neural network (NN) model using a pre-trained second NN model are disclosed. In an example, training data is input to the first and second models. The training data includes masked tokens and unmasked tokens. In response, the first model generates a first prediction associated with a masked token and a second prediction associated with an unmasked token, and the second model generates a third prediction associated with the masked token and a fourth prediction associated with the unmasked token. The first model is trained, based at least in part on the first, second, third, and fourth predictions. In another example, a prediction associated with a masked token, a prediction associated with an unmasked token, and a prediction associated with whether two sentences of training data are adjacent sentences are received from each of the first and second models. The first model is trained using the predictions.

Abstract: Methods, systems and computer program products for automated testing of dialog systems are provided herein. A computer-implemented method includes receiving information pertaining to a given conversation workspace of an automated dialog system and identifying test case inputs to the automated dialog system, the test case inputs comprising user input for the given conversation workspace that has portions thereof modified and which the automated dialog system maps to a different intent and/or a different entity relative to the user input. The method further includes generating human-interpretable explanations of mappings of portions of the test case inputs to the different intent and/or entity, generating suggestions for modifying intents, entities and dialog flows of the given conversation workspace such that the test case inputs map to the same intent and/or the same entity as their corresponding user input, and outputting the suggestions and the human-interpretable explanations to a user.

Abstract: A method for operating a voice trigger is provided. In some implementations, the method is performed at an electronic device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a sound input. The sound input may correspond to a spoken word or phrase, or a portion thereof. The method includes determining whether at least a portion of the sound input corresponds to a predetermined type of sound, such as a human voice. The method includes, upon a determination that at least a portion of the sound input corresponds to the predetermined type, determining whether the sound input includes predetermined content, such as a predetermined trigger word or phrase. The method also includes, upon a determination that the sound input includes the predetermined content, initiating a speech-based service, such as a voice-based digital assistant.

Abstract: The in-home care of seniors is augmented using Internet of Things (IOT) technologies. In-home sensors monitor a senior and their caregiver. Physical conditions and psychological conditions may be monitored. In some implementations, a machine learning system has a classifier trained to detect a specified condition, such as depression. The system may perform various transformations of raw sensor data into a format indicative of a particular condition. In one implementation, a psychological or medical condition has symptoms in which each symptom has one or more measurable events. Mappings between symptoms, events, sensor data, and sensor transformation functions may be supported.

Abstract: A method for configuring natural language grammars is provided to include identifying a first transcription having a first automatic speech recognition (ASR) score and a first natural language understanding (NLU) score and identifying a second transcription having a second ASR score and a second NLU score. The method includes detecting that a difference between the first and second ASR scores has a signed value with an opposite sign than a sign of a signed value of a difference between the first and second NLU scores, and responsive to detecting the opposite sign providing, to an evaluator, the audio query and the first and second transcriptions, receiving, from the evaluator, an indication of which of the first and second transcriptions is a correct transcription, and adjusting a value implemented to calculate the first NLU score or a value implemented to calculate the second NLU score.

Abstract: The present disclosure describes a system to use conversation data of patients to detect dangerous mental or physical conditions, such as suicidal thoughts, physical abuse, recent falls, and viral infection. A machine learning system may be trained to identify a dangerous mental or physical condition from conversations based on examples of patients evaluated to have a specific mental or physical condition. Conversations of patients may be monitored, natural language understanding (NLU) processing performed, and a machine learning system used to detect dangerous mental or physical conditions.

Abstract: A management system controls smart devices in a home by speech input without need of an internet connection or wireless or wired router. The system processes audio input and generates command signals for controlling the addressed smart device(s) using an industry standard protocol. The system allows the user to remove or add any kind of smart device within a residential environment.

Abstract: The present disclosure discloses a control method and a control apparatus for speech interaction. The detailed implementation solution of the control method for the speech interaction includes: collecting an audio signal; detecting a wake-up word in the audio signal to obtain a wake-up word result; and playing a prompt tone and/or executing a speech instruction in the audio signal based on the wake-up word result.

Abstract: A computer-implemented method is disclosed for determining one or more characteristics of a dialog between a computer system and user. The method may comprise receiving a system utterance comprising one or more tokens defining one or more words generated by the computer system; receiving a user utterance comprising one or more tokens defining one or more words uttered by a user in response to the system utterance, the system utterance and the user utterance forming a dialog context; receiving one or more utterance candidates comprising one or more tokens; for each utterance candidate, generating an input sequence combining the one or more tokens of each of the system utterance, the user utterance, and the utterance candidate; and for each utterance candidate, evaluating the generated input sequence with a model to determine a probability that the utterance candidate is relevant to the dialog context.

Abstract: Systems and processes for operating an intelligent automated assistant to perform intelligent list reading are provided. In accordance with one example, a method includes, at an electronic device having one or more processors, receiving a natural-language input corresponding to a domain; providing the natural-language input to an external device; receiving, from the external device, a process flow corresponding to the domain; determining, with the process flow corresponding to the domain, a task associated with the natural-language input; performing the task; and providing an output indicating whether the task has been performed.

Abstract: Embodiments are directed to summarizing conversational speech. Conversation segments may be provided based on a conversation stream and segmentation models. Summarization models may be determined based on characteristics of the conversation segments. Summarization information may be generated for each of the conversation segments based on the summarization models such that the summarization information includes a text-based summarization of the conversation segment. Summarization profiles may be generated for the conversation segments based on the summarization information such that each summarization profile is associated with quality scores. Summarization models may be modified based on the summarization profiles and the associated quality scores such that the summarization profiles are updated based on the modified summarization models. Modified summarization models and the updated summarization profiles may be employed to provide reports to a user.

Abstract: A voice input apparatus inputs voice and detects proximity to the voice input apparatus. The voice input apparatus performs control to, in a case where a second voice instruction for operating the voice input apparatus is input in a fixed period after a first voice instruction for enabling operations by voice on the voice input apparatus is input, execute processing corresponding to the second voice instruction. In a case where proximity to the voice input apparatus is detected, the voice input apparatus executes processing corresponding to the second voice instruction when the second voice instruction is input, even in a case where the first voice instruction is not input.

Abstract: A method for operating a voice trigger is provided. In some implementations, the method is performed at an electronic device including one or more processors and memory storing instructions for execution by the one or more processors. The method includes receiving a sound input. The sound input may correspond to a spoken word or phrase, or a portion thereof. The method includes determining whether at least a portion of the sound input corresponds to a predetermined type of sound, such as a human voice. The method includes, upon a determination that at least a portion of the sound input corresponds to the predetermined type, determining whether the sound input includes predetermined content, such as a predetermined trigger word or phrase. The method also includes, upon a determination that the sound input includes the predetermined content, initiating a speech-based service, such as a voice-based digital assistant.

Abstract: An embodiment of the present invention provides a method of man-machine interaction, including: receiving first audio uploaded by a user through a client end, marking a start time and an end time of the first audio, and generating a first recognition result of the first audio using an audio decoder; determining whether the first audio is a short speech based on the start time and end time thereof, and in case of a short speech, generating a second recognition result of the second audio using the audio decoder upon receiving the second audio uploaded by the client end within a preset heartbeat protection time range, sending at least the first recognition result and the second recognition result to a language prediction model; and if it is determined that a combination of the recognition results constitutes a sentence, generating an answering instruction corresponding to the sentence, and sending the answering instruction together with a feedback time mark of the answering instruction to the client end.

Abstract: An intelligent voice enable device searching method and apparatus are disclosed. A method for searching a plurality of voice enable devices according to one embodiment of the present disclosure includes receiving first device information from a first device receiving a wake-up voice; searching a first account associated with the first device based on the first device information; searching devices of a first group registered in the first account; searching a second account associated with a second device other than the first device among the devices of the first group; searching devices of a second group registered in the second account; searching devices of a third group sharing an IP address with the devices of the first group or the devices of the second group; and selecting a voice enable device to respond to the wake-up voice among the devices of the first group, the second group, and the third group.

Abstract: An electronic apparatus is provided. The electronic apparatus includes: a memory configured to store at least one instruction; and a processor configured to execute the at least one instruction to: obtain usage information on an application installed in the electronic apparatus, obtain a natural language understanding model, among a plurality of natural language understanding models, corresponding to the application based on the usage information, perform natural language understanding of a user voice input related to the application based on the natural language understanding model corresponding to the application, and perform an operation of the application based on the preformed natural language understanding.