Abstract: A method implemented by a server communicably coupled to at least two devices, each device including camera(s), the devices being present within same real-world environment. The method includes: receiving, from the devices(s), images captured by respective cameras of the devices; identifying one of the devices whose camera has camera parameter(s) better than camera parameter(s) of camera of another of the devices; training neural network using images captured by camera of one of the devices as ground truth material and using images captured by camera of another of the devices as training material; generating correction information to correct images captured by camera of another of the devices using trained neural network; and correcting the images captured by the camera of the another of the device(s) by utilising the correction information at the server, or sending correction information to another of the devices for correcting the images.

Abstract: A speech-processing system may provide access to one or more virtual assistants via a voice-controlled device. A user may leverage a first virtual assistant to translate a natural language command from a first language into a second language, which the device can forward to a second virtual assistant for processing. The device may receive a command from a user and send input data representing the command to a first speech-processing system representing the first virtual assistant. The device may receive a response in the form of a first natural language output from the first speech-processing system along with an indication that the first natural language output should be directed to a second speech-processing system representing the second virtual assistant. For example, the command may be in the first language, and the first natural language output may be in the second language, which is understandable by the second speech-processing system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage medium, for training a neural network, wherein the neural network is configured to receive an input data item and to process the input data item to generate a respective score for each label in a predetermined set of multiple labels. The method includes actions of obtaining a set of training data that includes a plurality of training items, wherein each training item is associated with a respective label from the predetermined set of multiple labels; and modifying the training data to generate regularizing training data, comprising: for each training item, determining whether to modify the label associated with the training item, and changing the label associated with the training item to a different label from the predetermined set of labels, and training the neural network on the regularizing data.

Abstract: A multi-channel transformer acoustic model that processes a plurality of audio signals output by microphones of a microphone array and outputs probabilities for acoustic units of an utterance represented in the audio signals. The audio signals represent the individual microphones' respective capturing of the utterance. The multi-channel model may perform self-attention on embeddings of the audio signals and then cross-channel attention across the attended audio signals. The cross-channel attention may involve processing of signals relative to each other to model the relationships across channels within and across time frames. The multi-channel model may include a transducer to perform processing frame-by-frame.

Abstract: Disclosed herein are techniques for using a generative adversarial network (GAN) to train a semantic parser of a dialog system. A method described herein involves accessing seed data that includes seed tuples. Each seed tuple includes a respective seed utterance and a respective seed logical form corresponding to the respective seed utterance. The method further includes training a semantic parser and a discriminator in a GAN. The semantic parser learns to map utterances to logical forms based on output from the discriminator, and the discriminator learns to recognize authentic logical forms based on output from the semantic parser. The semantic parser may then be integrated into a dialog system.

Abstract: A multi-factor identification system is provided in which enrolled user authentication information is updated in the course of an authorization request based upon at least one of a confidence level of a match between a request first factor identifier, produced based upon first unique user identifying information received with the authentication request, and a respective matching enrolled first factor identifier and a confidence level of a match between a request second factor identifier, produced based upon second unique user identifying information received with the authentication request, and a respective matching enrolled second factor identifier.

Abstract: The present disclosure provides systems and methods to obtain feedback descriptive of autonomous vehicle failures. In particular, the systems and methods of the present disclosure can detect that a vehicle failure event occurred at an autonomous vehicle and, in response, provide an interactive user interface that enables a human located within the autonomous vehicle to enter feedback that describes the vehicle failure event. Thus, the systems and methods of the present disclosure can actively prompt and/or enable entry of feedback in response to a particular instance of a vehicle failure event, thereby enabling improved and streamlined collection of information about autonomous vehicle failures.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate text tags for games. In some implementations, a computer-implemented method to generate one or more text tags includes obtaining a plurality of chat transcripts, each chat transcript associated with a respective gameplay session of a respective game of a plurality of games. Each chat transcript includes content provided by participants in the gameplay session. The method further includes programmatically analyzing the plurality of chat transcripts to determine one or more characteristics for each game of the plurality of games, and generating a text tag for at least one game of the plurality of games based on the one or more characteristics of the at least one game.

Abstract: Various embodiments of the present disclosure performing conversation sentiment monitoring for a conversation data object. In various embodiments, a text block that can be resized is identified within a conversation data object and successive regularized sentiment profile generation iterations are performed until a regularized sentiment score of the block exceeds a regularized sentiment score threshold. A current regularized sentiment profile generation iteration involves determining a regularized sentiment score for the block based on an initial sentiment score, a subjectivity probability value, and, optionally, a stage-wise penalty factor. A determination is then made as to whether the score exceeds the threshold. If so, then a regularized sentiment profile of the conversation data object is updated based on the regularized sentiment score. If not, then the text block is resized and a subsequent regularized sentiment profile generation iteration is performed based on the resized block.

Abstract: A natural language processing system may select a synthesized speech quality using user profile data. The system may receive a natural language input and determine responsive output data. The system may, based at least in part on user profile data associated with the input, determine response configuration data corresponding to a quality of synthesized speech. The system may then determine further output data for presentation using the responsive output data and response configuration data.

Abstract: In an approach to digital twin enabled equipment diagnostics based on acoustic modeling, a real-time audio input of an asset is received from a mobile device. The real-time audio input is analyzed using one or more acoustic modeling algorithms to establish a deviation from a baseline, where the baseline is associated with a digital twin of the asset. Responsive to determining the deviation from the baseline exceeds a predetermined threshold, the user is iteratively directed to move the mobile device until a stopping criteria is met.

Abstract: Systems/methods for intelligent commissioning of an HVAC system provide a control node and at least a first network node coupled to communicate with the control node, the first network node configured to retrieve via a user interface objects configured at the control node, configure at least a second network node using the retrieved objects, and report the configuration of the second network node at the control node. A user interface of a first network node can access the objects at the control node. The first network node can apply the accessed objects to configure a second network node using a commissioning tool. The commissioning tool can be activated specifically for certain authorized HVAC personas or roles. The first network node can report the configuring at the control node. The commissioning tool can be voice-enabled to allow a single user to configure the HVAC system via voice commands.

Abstract: The present disclosure describes a system and method for providing dynamic remediation of a pluggable streaming device issue, such as a customer premises equipment (CPE) device. Sometimes, various features of the CPE device to begin to fail. For example, synchronization of the audio and video streams may drift, media rental purchases may time out, or playback may throttle to low quality. Such failures can be caused by device or network issues. The present disclosure describes a CPE remediation system that operates to identify a failure associated with playing media streamed by the CPE device. The CPE remediation system may further determine a solution to remediate an observed CPE device-related failure. In some examples, the CPE remediation process may further provide or perform one or more actions included in the determined solution. In some examples, the solution may include a warm or a cold reboot.

Abstract: A method, computer program product, and computing system for synchronizing machine vision and audio is executed on a computing device and includes obtaining encounter information of a patient encounter, wherein the encounter information includes machine vision encounter information and audio encounter information. The machine vision encounter information and the audio encounter information are temporally-aligned to produce a temporarily-aligned encounter recording.

Abstract: The present disclosure relates to a virtual counseling system in which a user can virtually receive counseling by inputting query information into a system. A virtual counseling system according to an embodiment of the present disclosure may include an input unit obtaining audio information from a user and generating audio data; a determination unit receiving the audio data through the input unit, determining a type of the audio data, and generating type information on the audio data; and a text data generation unit generating object data by receiving the type information from the determination unit, converting content of the audio data into first text data, and combining the object data and the first text data to generate second text data.

Abstract: A voice recognition method includes the following steps. An audio and a correct result are received. The audio is recognized, and a text file corresponding to the audio is output. The word error rate is determined by comparing the text file to the correct result. The word error rate is adjusted according to the weight of at least one important word, in order to calculate a professional score that corresponds to the text file. A determination is made as to whether the professional score is higher than a score threshold. In response to the professional score is higher than the score threshold, the text file, the audio, or the correct result corresponding to the professional score is sent to an engine training module for training.

Abstract: A method performed by an audio system comprising a headset. The method sends a playback signal containing user-desired audio content to drive a speaker of the headset that is being worn by a user, receives a microphone signal from a microphone that is arranged to capture sounds within an ambient environment in which the user is located, performs a speech detection algorithm upon the microphone signal to detect speech contained therein, in response to a detection of speech, determines that the user intends to engage in a conversation with a person who is located within the ambient environment, and, in response to determining that the user intends to engage in the conversation, adjusts the playback signal based on the user-desired audio content.

Abstract: Systems and methods for detecting demographic bias in automatic speech recognition (ASR) systems. Corpuses of transcriptions from different demographic groups are analyzed, where one of the groups is known to be susceptible to bias and another group is known not to be susceptible to bias. A difference between the transcription accuracy for the first group and a transcription accuracy for a second group is measured. ASR accuracy for each group is measured and compared to each other using both statistics-based and practicality-based methodologies to determine whether a given ASR system or model exhibits a meaningful level of bias. Based on the statistical significance and the practical significance, an alert including a recommendation to adjust the ASR model is generated.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identity management are disclosed. In one aspect, a method includes the actions of receiving, from a first computing device, first audio data that includes representations of one or more words in a first voice. The actions further include generating second audio data that includes representations of the one or more words in a second voice. The actions further include providing, for output to a second computing device, the second audio data.

Abstract: A system is provided to categorize voice prints during a voice authentication. The system includes a processor and a computer readable medium operably coupled thereto, to perform voice authentication operations which include receiving an enrollment of a user in the biometric authentication system, requesting a first voice print comprising a sample of a voice of the user, receiving the first voice print of the user during the enrollment, accessing a plurality of categorizations of the voice prints for the voice authentication, wherein each of the plurality of categorizations comprises a portion of the voice prints based on a plurality of similarity scores of distinct voice prints in the portion to a plurality of other voice prints, determining, using a hidden layer of a neural network, one of the plurality of categorizations for the first voice print, and encoding the first voice print with the one of the plurality of categorizations.

Abstract: Aspects of the disclosure generally relate to computing devices and may be generally directed to devices, systems, methods, and/or applications for learning conversations among two or more conversation participants, storing this knowledge in a knowledgebase (i.e. neural network, graph, sequences, etc.), and enabling a user to simulate a conversation with an artificially intelligent conversation participant.

Abstract: Various techniques are disclosed, including receiving at a multiplatform management system a natural language request from a computing device, the multiplatform management system interfacing with multiple disparate platforms including a natural language processing platform, determining an event type based on the natural language request, identifying a user-requested action based on data associated with the natural language processing platform in data communication with the multiplatform management system, selecting a cloud platform to perform the user-requested action, formatting data representing the user-requested action into a formatted user-requested action, and performing the action.

Abstract: Contact centers strive to provide a positive and productive customer-agent interaction to successfully resolve the issue for a call. While audio content, such as music or messages, on hold are commonplace, selecting audio enhancements to be inserted into, and concurrently with, the customer-agent provides the customer and/or agent with cues and motivations to promote the successful completion of the call. Cues may be provided to announce the arrival or departure of an agent, virtually take a customer from one location to another for a different portion of the interaction, add excitement and anticipation to an upcoming event by providing an audio experience foreshadowing of the actual event, calm frayed nerves, or other purpose.

Abstract: Provided is a display apparatus for displaying an operation menu associated with a data processing performed on handwritten data, wherein the operation menu includes information related to the data processing according to a display position of the operation menu.

Abstract: A sound association system identifies one or more aurally active words in digital text. Aurally active words refer to words that denote particular sounds. Context-based sounds corresponding to the one or more aurally active words are also identified. Each context-based sound is anchored to or associated with the corresponding one or more aurally active words and is played back when the digital text is played back or read, providing context-based background sounds associated with the one or more aurally active words. For example, a context-based sound can be played back at a higher volume when the one or more aurally active words are played back or read, and at a lower volume when other words of the digital text are played back or read.

Abstract: A wrist terminal includes a communicator, timer, and at least one processor. The communicator receives a beacon ID transmitted from a beacon transmitter installed in a workplace. The timer obtains date-and-time information on a date and time at which the communicator receives the beacon ID. The processor performs a determining process and recording process. In the determining process, the processor determines whether a work status in the workplace is a work start or a work end, based on a state of the wrist terminal when the communicator receives the beacon ID. In the recording process, the processor records, in a storage, log information that includes the date-and-time information obtained by the timer and work status information on the work status determined in the determining process, the date-and-time information and the work status information being associated with each other.

Abstract: A method of detecting live speech comprises: receiving a signal containing speech; obtaining a first component of the received signal in a first frequency band, wherein the first frequency band includes audio frequencies; and obtaining a second component of the received signal in a second frequency band higher than the first frequency band. Then, modulation of the first component of the received signal is detected; modulation of the second component of the received signal is detected; and the modulation of the first component of the received signal and the modulation of the second component of the received signal are compared. It may then be determined that the speech may not be live speech, if the modulation of the first component of the received signal differs from the modulation of the second component of the received signal.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating a commentary. The method may include: acquiring at least one news cluster composed of pieces of news generated within a first preset time length, the pieces of news in the news cluster direct to a given news event; determining a target news cluster based on the at least one news cluster; determining, for each piece of news in the target news cluster, a score of being suitable for generating a commentary for the piece of news; and generating, based on a piece of target news, a commentary for the target news cluster, where the piece of target news is a piece of news having a highest score of being suitable for generating a commentary in the target news cluster.

Abstract: The present invention relates to a brain-computer interface system and a method for recognizing a conversation intention of a user using the same in addition to inferring the waveform of word sound intended by a user from an imagined speech brainwave associated with a word intended by a user, since the user can intuitively recognize the sentence he/she wants to speak through the imagined speech by classifying words that are most relevant to the imagined speech brainwave of the user in a database in which a word often used by the user or frequently used in a specific situation is stored and by generating a sentence intended by the user by recognizing the words classified in this way, it is possible to perform communication by only thoughts of the user.

Abstract: Systems and methods are described herein to automate managing of service layer operations comprised of multiple elementary operations and offloading the burden of performing such multi-step operations from a requesting entity to the service layer. A Request Abstraction Service (RAS) is described herein for the autonomous execution of such multi-step operations. Methods and apparatuses are also described herein for a service layer framework for integrating generic and functional user interfaces as services managed by the SL on behalf of requesting entities.

Abstract: A low cost DAB multichannel receiver comprising a simplified buffering method for buffering content segments from multiple streams contained within the DAB channel, where the receiver enables the listener to navigate buffered content segments from multiple streams within the DAB channel while enabling the broadcaster to control the timeshift of commercial content to the receiver output stream. The receiver's buffered content grows over time and is cleared when tuning away from the channel, thus encouraging listeners desiring to tune in to new content to instead navigate to new buffered segments. Broadcaster control of the listener experience may be enabled by setting content control fields which are observed in the broadcast by the multichannel receivers. Additional embodiments are disclosed.

Abstract: Systems and methods for detecting demographic bias in automatic speech recognition (ASR) systems. Corpuses of transcriptions from different demographic groups are analyzed, where one of the groups is known to be susceptible to bias and another group is known not to be susceptible to bias. ASR accuracy for each group is measured and compared to each other using both statistics-based and practicality-based methodologies to determine whether a given ASR system or model exhibits a meaningful level of bias.

Abstract: Systems and methods are described herein to automate managing of service layer operations comprised of multiple elementary operations and offloading the burden of performing such multi-step operations from a requesting entity to the service layer. A Request Abstraction Service (RAS) is described herein for the autonomous execution of such multi-step operations. Methods and apparatuses are also described herein for a service layer framework for integrating generic and functional user interfaces as services managed by the SL on behalf of requesting entities.

Abstract: System and methods for processing audio signals are disclosed. In one implementation, a system may comprise a wearable camera configured to capture images from an environment of a user; a microphone; and a processor. The processor may be configured to receive an audio signal representative of sounds captured by the microphone during a time period; and receive the images captured by the wearable camera. The processor may process the audio signal in a first mode based on audio data accumulated in a buffer prior to the time period; detect a change in the active speaker from the first individual to a second individual; and cease processing in the first mode and process the audio signal in a second mode that differs from the first mode.

Abstract: A conversation topic providing method includes: converting voice data, of a conversation of a user who is on a phone, into text; selecting a keyword, indicating an intention of the user, from the text; obtaining information of interest with respect to the keyword; and determining topics relating to the keyword based on user information.

Abstract: Among other things, requests are received from voice assistant devices expressed in accordance with different corresponding protocols of one or more voice assistant frameworks. Each of the requests represents a voiced input by a user to the corresponding voice assistant device. The received requests are re-expressed in accordance with a common request protocol. Based on the received requests, responses to the requests are expressed in accordance with a common response protocol. Each of the responses is re-expressed according to a protocol of the framework with respect to which the corresponding request was expressed. The responses are sent to the voice assistant devices for presentation to the users.

Abstract: A method and system for determining a respiratory rate of a user using an electrocardiogram (ECG) segment of the user are disclosed. The method comprises decomposing the ECG segment into a plurality of functions and evaluating the plurality of functions to choose one of the plurality of functions based on a respiratory band power. The method includes determining the respiratory rate using the one of the plurality of functions and a domain detection.

Abstract: One embodiment provides a method for predicting a next action in a conversation system that includes obtaining, by a processor, information from conversation logs and a conversation design. The processor further creates a dialog graph based on the conversation design. Weights and attributes for edges in the dialog graph are determined based on the information from the conversation logs and adding user input and external context information to an edge attributes set. An unrecognized user input is analyzed and a next action is predicted based on dialog nodes in the dialog graph and historical paths. A guiding conversation response is generated based on the predicted next action.

Abstract: A prosodic speech recognition engine configured to identify prosodic features and patterns in a speech continuum for the extraction of linguistic content including para-syntactic content, discourse function, information structure, meaning, and speaker sentiment.

Abstract: An interactive system and method for development of the voice, preferably for singing. The system and methods provide and utilize an animated, interactive, preferably 3D, visual character for illustrating the various human physiological components involved in producing vocals, and how best to strengthen and train such components to prevent injury. The system and methods are designed to visually replicate how the human body, and more specifically the internal organs for voice, interact and synchronize muscular movements that are involved in abdominal support, release of air control, and neural stimulation, in unison with Larynx mobility and gravity.

Abstract: A sound pickup transducer array, deployed within an enclosed area, is coupled to a sound recorder. A processor, coupled to the sound recorder, provides a button or speech recognizer through which a person in the enclosed area issues a command signifying the occurrence of a sound for which categorizing is requested. The processor is programmed to respond to the issued command by extracting and storing an audio snippet copied from the audio recorder, in a digital memory, where the snippet corresponds to sound captured before, during and after the issued command. The processor communicates the stored audio snippet to an artificial intelligence system trained to categorize sounds as to what produced them. The artificial intelligence system may employ trained model feature extraction, a neural network categorization system, and/or direction of sound arrival analysis.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed. An example apparatus includes a controller to cause a people meter to emit a prompt for input of audience identification information at a first time and determine a first audience count based on the input, an audio detector to determine a second audience count based on signatures generated from audio data captured in the media environment, and a comparator to cause the people meter to not emit the prompt for at least a first time period after the first time when the first audience count is equal to the second audience count.

Abstract: Disclosed herein is a robot including an output interface including at least one of a display or a speaker, and a processor configured to acquire output data of a predetermined playback time point of content output via the robot or an external device, recognize a first emotion corresponding to the acquired output data, and control the output interface to output an expression based on the recognized first emotion.

Abstract: Systems and processes for intelligent device identification are provided. In one example process, audio input may be sampled with a microphone at each of two or more of the plurality of electronic devices. A first electronic device of the plurality of electronic devices for determining a task associated with sampled audio input may be identified. The process may determine the task based on the sampled audio input with the first electronic device and identify identifying a second electronic device of the plurality of electronic devices for performing the task. The task be performed with the second electronic device. The second electronic device is not the first electronic device in some examples.

Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device may receive an input audio signal (e.g., including both an external signal and a self-voice signal). The wearable device may detect the self-voice signal in the input audio signal based on a self-voice activity detection (SVAD) procedure, and may implement the described techniques based thereon. The wearable device may perform beamforming operations or other separation procedures to isolate the external signal and the self-voice signal from the input audio signal. The wearable device may apply a first filter to the external signal, and a second filter to the self-voice signal. The wearable device may then mix the filtered signals, and generate an output signal that sounds natural to the user.

Abstract: An in-vehicle apparatus is connectable to a device that includes a voice assistant function. The in-vehicle apparatus includes: a voice detector that performs voice recognition of an audio signal input from a microphone and that controls functions of the in-vehicle apparatus based on a result of the voice recognition; and an interface that communicates with the device. When being informed of a detection of a predetermined word in the audio signal as the result of the voice recognition of the audio signal performed by the voice detector, the interface sends to the device, not via the voice detector, the audio signal input from the microphone. The predetermined word is for activating the voice assistant function of the device.

Abstract: Methods and systems are described herein for improving audio for hearing impaired content consumers. An example method may comprise determining a content asset. Closed caption data associated with the content asset may be determined. At least a portion of the closed caption data may be determined based on a user setting associated with a hearing impairment. Compensating audio comprising a frequency translation associated with at least the portion of the closed caption data may be generated. The content asset may be caused to be output with audio content comprising the compensating audio and the original audio.

Abstract: A jitter buffer control for controlling a provision of a decoded audio content on the basis of an input audio content is configured to select a frame-based time scaling or a sample-based time scaling in a signal-adaptive manner. An audio decoder uses such a jitter buffer control.

Abstract: A contact center analysis system can receive various types of communications from customers, such as audio from telephone calls, voicemails, or video conferences; text from speech-to-text translations, emails, live chat transcripts, text messages, and the like; and other media or multimedia. The system can segment the communication data using temporal, lexical, semantic, syntactic, prosodic, user, and/or other features of the segments. The system can cluster the segments according to one or more similarity measures of the segments. The system can use the clusters to train a machine learning classifier to identify one or more of the clusters as waypoints (e.g., portions of the communications of particular relevance to a user training the classifier). The system can automatically classify new communications using the classifier and facilitate various analyses of the communications using the waypoints.

Abstract: Systems and methods include receiving, with a processor, two or more messages from a first user device participating in a communication session, processing, with the processor, the two or more messages, generating, with the processor, a processed message, and displaying, with the processor, the processed message on a second user device participating in the communication session.