Abstract: Virtual assistants intelligently emulate a representative of a service provider by providing variable responses to user queries received via the virtual assistants. These variable responses may take the context of a user's query into account both when identifying an intent of a user's query and when identifying an appropriate response to the user's query.

Abstract: Disclosed is a method for separating a speech based on artificial intelligence in a vehicle. The method includes separating a speech signal using at least one sound beam-forming or source separation; and performing a speech recognition function by detecting a speaker (user) of the separated signal, and accordingly, other users in the vehicle in addition to a driver may use the speech recognition function. A device and method for separating speech based on artificial intelligence in vehicle of the present disclosure can 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: A computerized method for analyzing a zoning ordinance comprises converting the text into a raw text format; parsing the raw text format to establish a hierarchical structure; building a network representation of the text of the zoning ordinance; collecting examples of portions the zoning ordinance to be analyzed; building a language model of each subsection of the text of the zoning ordinance; running the language model on each subsection of the text of the zoning ordinance; correlating references to previously translated sections of the text of the zoning ordinance; outputting text of the zoning ordinance as a data dictionary with sections interpreted as machine readable code; and outputting simplified language sentences from the data dictionary. An assembled document comprising at least one of the machine readable code and the simplified language sentences is provided. Associated images can be included in the document. A programmed computer and a medium including computer code for practicing the method.

Abstract: A method of converting speech to text comprises receiving an audio recording from an input device comprising speech of a plurality of speakers. Extracting from the audio recording, a speaker audio recording comprising recorded audio of an individual speaker. Selecting, based on a characteristic of the speaker audio recording, a speech to text engine and a dictionary. Configuring the speech to text engine with the dictionary and executing a first conversion process to convert a first portion of the speaker audio recording to produce a first transcript. Evaluating a performance metric of the conversion process against a quality metric to reconfigure the speech to text engine and execute a second conversion process to convert a second portion of the speaker audio recording to produce a second transcript. Combining the first transcript and the second transcript to produce a transcript of the speaker audio recording.

Abstract: A system and method establishes a communication connection between a first device of a first user and a second device of a second user. Request data corresponding to a request to establish a communication connection with a second user is received, and a user profile associated with the second user is determined. One or more sensors of the second device receive input data corresponding to the environment of the second device, and an identity of the second user is determined based thereon. The communication connection is established and, based on the identity, the second device tracks movement of the second user in the environment.

Abstract: A portable gateway device for use with a Building Management System (BMS) enables voice command control of BMS devices. The portable gateway device comprises a Wi-Fi module, a serial communications interface, and a data conversion module. The Wi-Fi module is configured to enable communication with a user device via Wi-Fi. The portable gateway device is configured to receive a voice command spoken by a user of the user device. The serial communications interface is configured to enable communication with a bus connected to a BMS device. The data conversion module is configured to translate the voice command received from the user device into a control action associated with the BMS device. The portable gateway device is configured to provide the control action to the BMS device via the serial communications interface. The control action affects a state or condition of the BMS device.

Abstract: The present disclosure relates generally to a system and method for voice development frameworks. Certain cloud-based systems may be embodied in a multi-instance or multi-tenant framework, and may provide for certain computing systems and resources. For example, the cloud-based systems may provide for data repositories and the creation of executable objects, e.g., Flow Designer objects that include voice commands. In certain embodiments, visual development tools, including a Flow Designer system, may be used to create the executable objects, including voice command objects. For example, the Flow Designer system may enable the non-technical personnel to use natural language to more easily create and visualize objects and processes that automate certain tasks.

Abstract: A method of using voice commands from a mobile device to remotely access and control a computer. The method includes receiving audio data from the mobile device at the computer. The audio data is decoded into a command. A software program that the command was provided for is determined. At least one process is executed at the computer in response to the command. Output data is generated at the computer in response to executing at least one process at the computer. The output data is transmitted to the mobile device.

Abstract: The present disclosure generally relates to interview training and providing interview feedback. An exemplary method comprises: at an electronic device that is in communication with a display and one or more input devices: receiving, via the one or more input devices, media data corresponding to a user's responses to a plurality of prompts; analyzing the media data; and while displaying, on the display, a media representation of the media data, displaying a plurality of analysis representations overlaid on the media representation, wherein each of the plurality of analysis representations is associated with an analysis of content located at a given time in the media representation and is displayed in coordination with the given time in the media representation.

Abstract: Systems and methods for maintaining voice assistant persistence across multiple network microphone devices are described. In one example, first and second NMDs each identify a wake word based on detected sound, and are each transitioned from an inactive state to an active state in which the NMD captures and transmits sound data over a network interface. The first NMD is selected over the second NMD to output a first response, and both NMDs remain in the active state to further capture and transmit sound data. After further capturing and transmitting of sound data, the second NMD is selected over the first NMD to output a second response. After a predetermined time, one or both of the NMDs are transitioned back to the inactive state. The selection of one NMD over another for outputting a response can be based at least in part on user location information.

Abstract: A building automation system (BAS) is configured to support a variety of different natural language processing (NLP) service providers with minimal or no redesign effort. The BAS includes an event handler configured to receive an external request from a service provider. The external request is associated with a voice input uttered by a user. The BAS further includes an abstraction layer configured to receive the external request from the event handler and generate an internal request based on the external request. The BAS further includes an intent processor configured to receive the internal request from the abstraction layer and an intent handler in communication with the intent processor and configured to perform an action in accordance with the internal request.

Abstract: The present disclosure generally relates to interview training and providing interview feedback. An exemplary method comprises: at an electronic device that is in communication with a display and one or more input devices: receiving, via the one or more input devices, media data corresponding to a user's responses to a plurality of prompts; analyzing the media data; and while displaying, on the display, a media representation of the media data, displaying a plurality of analysis representations overlaid on the media representation, wherein each of the plurality of analysis representations is associated with an analysis of content located at a given time in the media representation and is displayed in coordination with the given time in the media representation.

Abstract: An apparatus and method are disclosed for processing an audio signal. The apparatus includes an input interface, a digital filterbank having an analysis part and a synthesis part, a first phase shifter, a spectral envelope adjuster, a second phase shifter, and an output interface. The first phase shifter and the second phase shifter reduce a complexity of the digital filterbank, which includes both analysis and synthesis filters that are complex-exponential modulated versions of a prototype filter.

Abstract: The present disclosure relates to systems and methods for speech signal processing on a signal to transcribe speech. In one implementation, the system may include a memory storing instructions and a processor configured to execute the instructions. The instructions may include instructions to receive the signal, determine if at least a portion of data in the signal is missing, and when at least a portion of data is missing: process the signal using a hidden Markov model to generate an output; using the output, calculate a set of possible contents to fill a gap due to the missing data portion, with each possible content having an associated probability; based on the associated probabilities, select one of the set of possible contents; and using the selected possible content, update the signal.

Abstract: A method and an apparatus for voiceprint creation and registration, comprising: prompting to create a voiceprint and register when a device is enabled for a first time(101); using a text-related training method to create a voiceprint model for a user(102); generating an ID for the user(103); and prompting the user to input user ID-related data; storing the ID for the user and the voiceprint model correspondingly in a voiceprint registration database(104). The problems in the prior art that the technology of the voiceprint creation and registration method has a high learning cost and is more disturbing to the user may be avoided. The voiceprint creation process may cover various scenes, the voiceprint creation may guide the user in all stages, or the voiceprint creation is separated from registration through a frequency to minimize user's disturbance, and after the user is guided to register the voiceprint, the speech interaction product may provide personalized service to the user based on the voiceprint.

Abstract: Systems and methods for media playback via a media playback system include capturing sound data via a network microphone device and identifying a candidate wake word in the sound data. Based on identification of the candidate wake word in the sound data, the system selects a first wake-word engine from a plurality of wake-word engines. Via the first wake-word engine, the system analyzes the sound data to detect a confirmed wake word, and, in response to detecting the confirmed wake word, transmits a voice utterance of the sound data to one or more remote computing devices associated with a voice assistant service.

Abstract: The present disclosure is directed to optimizing transfer learning for neural networks by creating a dynamic transfer network configuration through gated architecture. In some embodiments, transfer learning implements multiple parameter sharing schemes across a source task and a target task. The gating architecture can learn the optimal parameter sharing schemes as the neural network is trained. In some embodiments, the system can be used in named entity recognition applications where the training data is limited.

Abstract: A determination unit (7) determines whether or not a specific passenger in a car has spoken, on the basis of sound data collected in the car. A control unit (8) activates an in-car communication function, when it is determined by the determination unit (7) that the specific passenger has spoken.

Abstract: A non-transitory computer-readable recording medium stores therein an output control program that causes a computer to execute a process including: receiving a phoneme string for a text having a plurality of sentences; determining a sentence corresponding to a specific phoneme or a phoneme string included in the received phoneme string; referring to a storage that stores therein co-occurrence information on sentences for words in association with the words and determining a word the co-occurrence information on the determined sentence of which satisfies a standard among the words; changing the specific phoneme or the phoneme string included in the received phoneme string to the determined word to generate a text corresponding to the received phoneme string; and outputting the generated text.

Abstract: Various embodiments are provided for understanding user sentiment in a dialog system in a computing environment by a processor. A sentiment of a user may be detected according to a sentiment analysis and user feedback during a dialog with the user. One or more reasons for the sentiment of the user may be identified. Behavior of the dialog system may be adjusted according to the one or more reasons.