Abstract: The present disclosure relates to a method, apparatus, and system for speaker verification. The method includes: acquiring an audio recording; extracting speech signals from the audio recording; extracting features of the extracted speech signals; and determining whether the extracted speech signals represent speech by a predetermined speaker based on the extracted features and a speaker model trained with reference voice data of the predetermined speaker.

Abstract: An audio processor for processing an audio signal includes an audio signal phase measure calculator configured for calculating a phase measure of an audio signal for a time frame, a target phase measure determiner for determining a target phase measure for the time frame, and a phase corrector configured for correcting phases of the audio signal for the time frame using the calculated phase measure and the target phase measure to obtain a processed audio signal.

Abstract: A computing system is provided. The computing system includes a processor of a display device configured to execute one or more programs. The processor is configured to receive a command from a user by way of natural language input. The processor is configured to identity a set of candidate objects within or adjacent a user's field of view having associated spatialized regions on which the command can be executed, the set of candidate objects identified at least partially by using a machine learning model. The processor is configured to use visual or audio indicators associated with the candidate objects and query the user for disambiguation input. The processor is configured to receive the disambiguation input from the user that selects a target object, executing the command on the target object. The processor is configured to train the machine learning model using the disambiguation input and data about the spatialized regions.

Abstract: System and methods for controlling healthcare devices and systems using voice commands are presented. In some aspects a listening device may receive voice command from a person. The voice command may be translated into human readable or machine readable text via a speech-to-text service. A control component may receive the text and send device-specific instructions to a medical device associated with a patient based on the translated voice command. In response to the instructions, the medical device may take an action on a patient. Some examples of actions taken may include setting an alarm limit on a monitor actively monitoring a patient and adjusting the amount of medication delivered by an infusion pump. Because these devices may be controlled using a voice command, in some cases, no physical or manual interaction is needed with the device. As such, multiple devices may be hands-free controlled from any location.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.

Abstract: A system receives a first voice input from a first user, such as a baby or a person who has had a stroke. Although the first user intends to communicate a particular meaning, the first voice input is not in a language that is known to the system and thus the system does not know the particular meaning that the first user intended. After receiving the first voice input, a second voice input is received from a second user. This second voice input is in a language that is known to the system. The system determines a meaning of the second voice input, associates this meaning with the first voice input, and uses this association to train a machine learning system. This machine learning system is used to attempt to understand the meaning of subsequent voice inputs received from the first user.

Abstract: A system and method for providing natural training to an AI/agent/bot. In one embodiment, the system and method include receiving a first input indicating a trainer's desire to provide knowledge or know-how to an artificially-intelligent agent; creating a first natural training session to capture the knowledge or know-how; receiving the knowledge or know-how from the trainer; sending a first response to the trainer, the first response requesting a first prompt that, when received by the artificially-intelligent agent, prompts the artificially-intelligent agent to use the knowledge or know-how captured in the first natural training session to respond; receiving a second input from the trainer including a first prompt; validating a capability of the artificially-intelligent agent to correctly respond to requests related to the knowledge or know-how captured by the first training session; and receiving additional.

Abstract: A parse tree corresponding to a portion of narrative text is constructed. The parse tree includes a data structure representing a syntactic structure of the portion of narrative text as a set of tokens according to a grammar. Using a token in the parse tree as a focus word, a context window comprising a set of words within a specified distance from the focus word is generated, the distance determined according to a number of links of the parse tree separating the focus word and a context word in the set of words. A weight is generated for the focus word and the context word. Using the weight, a first vector representation of a first word is generated, the first word being within a second portion of narrative text.

Abstract: An output device includes a memory and a processor coupled to the memory. The processor obtains an utterance command and an action command, analyzes an utterance content of the utterance command inputted after an action performed in response to the action command, modifies the action command based on a result of the analysis, and outputs the modified action command and the utterance command.

Abstract: An electronic device is provided. The electronic device according to an embodiment includes a microphone, a communicator comprising communication circuitry, and a processor configured to control the communicator to transmit a control command to an external audio device for reducing an audio output level of the external audio device in response to a trigger signal for starting a voice control mode being received through the microphone and to control the electronic device to operate in the voice control mode.

Abstract: Disclosed is a method, a device, a system and/or a manufacture of control and security of a voice controlled device. In one embodiment, an apparatus includes a signal input for receiving a command signal and a soundwave damper to dampen a sound receiving capability of a voice controlled device. The voice controlled device is capable of initiating a responsive action in response to a voice command. A processor determinations that the command signal is associated with the voice command and in response to the determination generate with a speaker a soundwave carrying the voice command bypassing the soundwave damper such that the soundwave carrying the voice command is communicable to the microphone of the voice controlled device. The apparatus also includes a cap housing the speaker and optionally the soundwave damper. As an example, the soundwave damper may be a barrier, a flexible membrane, or a sound interference generator.

Abstract: Detecting overnegation in text is provided. A plurality of word lists are compiled. An input text is received. One or more combined weightings are determined, wherein each combined weighting is based, at least in part, on a portion of the input text and the plurality of word lists. A total overnegation score of the input text is generated based, at least in part, on a statistical aggregation of the one or more combined weightings. In response to determining that the total overnegation score exceeds a pre-determined threshold, it is determined that the input text contains a logical error. In response to the total overnegation score exceeding a pre-determined level, one or more actions are executed.

Abstract: A software agent, that is used to assist in providing a service, receives communications from a set of users that are attempting to use the software agent. The communications include communications that are interacting with the software agent, and communications that are not interacting with the software agent. The software agent performs natural language processing on all communications to identify such things as user sentiment, user concerns or other items in the content of the messages, and also to identify actions taken by the users in order to obtain a measure of user satisfaction with the software agent. One or more action signals are then generated based upon the identified user satisfaction with the software agent.

Abstract: A method, device, and storage medium for converting text to speech are described. The method includes obtaining target text; synthesizing first machine speech corresponding to the target text; and selecting an asynchronous machine speech whose prosodic feature matches a prosodic feature of the first machine speech from an asynchronous machine speech library. The method also includes searching a synchronous machine speech library for a first synchronous machine speech corresponding to the asynchronous machine speech; synthesizing, based on a prosodic feature of the first synchronous machine speech, second machine speech corresponding to the target text; and selecting a second synchronous machine speech matching an acoustic feature of the second machine speech from the synchronous machine speech library. The method further includes splicing speaker speech units corresponding to the synchronous machine speech unit in a speaker speech library, to obtain a target speaker speech.

Abstract: The present disclosure describes a communication environment having a service provider server that receives an audio command from a display control device within the communication environment. The service provider server can translate this audio command into an electrical command for controlling the display device. The service provider server autonomously performs a specifically tailored search of a catalog of command words and/or phrases for the audio command to translate the audio command to the electrical command. This specifically tailored search can include one or more searching routines having various degrees of complexity. The most simplistic searching routine from among these searching routines represents a textual search to identify one or more command words and/or phrases from the catalog of command words and/or phrases that match the audio command.

Abstract: Processing sound received by a device can include receiving a first signal from a first microphone of the device and a second signal from a second microphone of the device, where the first and second microphones capture sounds from a sound field. A ratio between the acoustic pressure and the particle velocity of the sound field can be calculated. In response to the ratio exceeding a threshold, speech signal processing is performed on one or more of the microphone signals. Other aspects are also described and claimed.

Abstract: An in-vehicle voice recognition apparatus capable of recognizing user voice more correctly by removing sound generated in a vehicle from sound input to a microphone, and a method of controlling the same are disclosed. The in-vehicle voice recognition apparatus according to an embodiment of the present disclosure includes a central processing unit configured to output a media signal, a digital signal processor configured to receive the media signal from the central processing unit and to convert the media signal into an analog signal, and an eco cancellation hardware connected to the digital signal processor and configured to receive the analog signal, to acquire a first final media output on the basis of the analog signal and to acquire a voice command from a sound input through a microphone on the basis of the first final media output.

Abstract: A device may be configured to parse a syntax element specifying the number of available languages within a presentation associated with an audio stream. A device may be configured to parse one or more syntax elements identifying each of the available languages and parse an accessibility syntax element for each language within the presentation.

Abstract: The disclosure relates to a human-machine interface (HMI) for a vehicle having a microphone for registering a command word spoken by a driver or further occupant of the vehicle and a control unit, which has a speech recognition module for recognizing multiple specific command words.

Abstract: Techniques are provided for training a language recognition model. For example, a language recognition model may be maintained and associated with a reference language (e.g., English). The language recognition model may be configured to accept as input an utterance in the reference language and to identify a feature to be executed in response to receiving the utterance. New language data (e.g., other utterances) provided in a different language (e.g., German) may be obtained. This new language data may be translated to English and utilized to retrain the model to recognize reference language data as well as language data translated to the reference language. Subsequent utterances (e.g., English utterances, or German utterances translated to English) may be provided to the updated model and a feature may be identified. One or more instructions may be sent to a user device to execute a set of instructions associated with the feature.