Abstract: The present invention provides a voiceprint recognition method, a device, a storage medium and a background server. The voiceprint recognition method comprises: collecting, by a client, and sending a voice recognition request to the background server, the voice recognition request comprises the user ID and the test voice; receiving the voice recognition request, and determining the voice recognition request to be processed with a message queue and an asynchronous mechanism; acquiring a target voiceprint feature which corresponds to the user ID of the voice recognition request to be processed, and acquiring a test voiceprint feature which corresponds to the test voice of the voice recognition request to be processed; judging whether the target voiceprint feature and the test voiceprint feature correspond to the same user, and outputting the result of the judging to the client; and receiving and displaying, by the client, the result of the judging.

Abstract: It is desired that a technique be provided that is capable of ensuring more reliable voice communication during surgery among surgical participants. Provided is a control device including a sound-output-control unit that controls sound output by a sound-output device on a basis of information related to surgery.

Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.

Abstract: Systems and methods for providing media content recommendations. For example, a media guidance application may determine that a phrase spoken by a first user during a conversation with a second user indicates that the first user will not be consuming media content with the second user during a future time interval. In response to determining that the first user will not be consuming media content with the second user during the future time interval, the media guidance application may identify media assets available for consumption during the future time interval having a given characteristic favored by the second user and a characteristic disfavored by the first user. The media guidance application may then generate, for the future time interval, a media content recommendation of a media asset having the given characteristic, and generate for display, to the second user, the media content recommendation.

Abstract: An interactive device includes an authenticator for authenticating a user, a speech urger which urges the user to speak when the authenticator unsuccessfully authenticates the user, and an interaction controller which performs interaction according to the authenticated user when the authenticator successfully authenticates the user by a voice of the user having been urged to speak.

Abstract: A system and method for distinguishing the sentiment of utterances in a dialog is disclosed. The system utilizes a lexicon that is expanded from a seed using unsupervised machine learning. What results is a sentiment classifier that may be optimized for a variety of environments (e.g., conversation, chat, email, etc.), each of which may communicate sentiment differently.

Abstract: The A pattern recognition apparatus using domain adaptation 10 comprises an estimation unit 11. The estimation unit 11 estimates PLDA (Probabilistic Linear Discriminant Analysis) parameters and transformation parameters from features of a first domain data and a second domain data so as to maximize/minimize an objective function with respect to the features.

Abstract: Embodiments of systems, apparatuses, and/or methods are disclosed for automatic speech imitation. An apparatus may include a machine learner to perform an analysis of tagged data that is to be generated based on a speech pattern and/or a speech context behavior in media content. The machine learner may further generate, based on the analysis, a trained speech model that is to be applied to the media content to transform speech data to mimic data. The apparatus may further include a data analyzer to perform an analysis of the speech pattern, the speech context behavior, and/or the tagged data. The data analyzer may further generate, based on the analysis, a programmed speech rule that is to be applied to transform the speech data to the mimic data.

Abstract: A system, a computer program product, and method for controlling synthesized speech output on a voice-controlled device. A sensor is used to capture an image of a face of a person. A database of previously stored images of facial features is accessed. In response to i) not recognizing the at least one person the voice-controlled device selects a first set of conversational starters; ii) recognizing the person and recognizing previous communications with the person, the voice-controlled device selects a second set of conversational starters; iii) recognizing the person and not recognizing previous communications with the person, the voice-controlled device selects a third set of conversational starters; or iv) recognizing the at least one person and recognizing previous communications with the person selecting but do not know the person's name selecting a fourth set of conversational starters. The voice controlled device outputs the selected set of conversational starters.

Abstract: Embodiments of the present disclosure provide a method and a device for processing a voice message, a terminal and a storage medium. The method includes: receiving a voice message sent by a user, the voice message being obtained based on an unordered version of language interaction; determining a corresponding spectrum of frequency domain feature based on the voice message, and performing a signal processing on the spectrum of frequency domain feature to obtain a first acoustic feature based on frame sequence and corresponding to the spectrum of frequency domain feature; and performing a feature extraction on the first acoustic feature to obtain a second acoustic feature based on an ivector algorithm and a deep convolutional neural network algorithm with residual processing, converting the second acoustic feature into a voiceprint model corresponding to the user, and storing the voiceprint model in a voiceprint model database.

Abstract: A method for generating voiceprint information is provided. The method includes acquiring a historical voice file generated by a call between a first user and a second user; executing text recognition processing on the voice information to obtain text information corresponding to the voice information; and storing the voice information and the corresponding text information as reference voiceprint information of the first user, and storing an identifier of the first user. Furthermore each voiceprint information comprises a plurality of pieces of reference voiceprint information, each of which is sufficient to authenticate a user.

Abstract: A system configured to enable remote control to allow a first user to provide assistance to a second user. The system may receive a command from the second user granting remote control to the first user, enabling the first user to initiate a voice command on behalf of the second user. In some examples, the system may enable the remote control by enabling wakeword detection for incoming audio data, enabling a second device to detect a wakeword and corresponding voice command from incoming audio data originating from a first device. For example, the second device may disable and/or modify echo cancellation processing, enabling the second device to detect the voice command from audio output based on the incoming audio data and/or from the incoming audio data itself.

Abstract: The disclosed system addresses a technical problem tied to computer technology and arising in the realm of computer memory capacity, namely the technical problem of providing a flexible response dialogue system that can be utilised for a variety of different types of dialogue without requiring the system to be specifically trained for each situation. This therefore avoids the need for large amounts of labelled training data for each type of dialogue (each potential conversation flow or subject area for the conversation). The disclosed system solves this technical problem by using semantic similarity to match a user's input to one of a set of predefined inputs (predefined user responses). Various mechanisms are implemented to provide disambiguation in the event of multiple potential matches for the input. By using semantic similarity, the user's response in unconstrained. This therefore provides a user interface that is more user-friendly.

Abstract: A voice-activated camera system for a computing device. The voice-activated camera system includes a processor, a camera module, a speech recognition module and a microphone for accepting user voice input. The voice-activated camera system includes authorized for only a specific user's voice, so that a camera function may be performed when the authorized user speaks the keyword, but the camera function is not performed when an unauthorized user speaks the keyword.

Abstract: Techniques are disclosed for unlocking in-game content for a video game application. In one embodiment, the video game application may be operated by a user that is concurrently viewing media content. The video game application captures an audio signal from the concurrently-playing media content, performs content recognition on the captured audio signal, and determines whether to unlock one or more portions of in-game content based on the identified media content.

Abstract: A media generating and editing system that generates audio playback in alignment with text that has been automatically transcribed from the audio. A transcript data file that includes a plurality of text words transcribed from audio words included in the audio data is stored. Timing data is paired with the text words indicating locations in the audio data of the corresponding audio words from which the text words are transcribed. The audio data is provided for playback at a user device. The text words are displayed on a display screen at a user device and a visual marker is displayed on the display screen to indicate the text words on the display screen in time alignment with the audio playback of the corresponding audio words at the user device. The text words in the transcript data file are amended in response to inputs from the user device.

Abstract: Technologies for automatic speech recognition using articulatory parameters are disclosed. An automatic speech recognition device may capture speech data from a speaker and also capture an image of the speaker. The automatic speech recognition device may determine one or more articulatory parameters based on the image, such as such as a jaw angle, a lip protrusion, or a lip height, and compare those parameters with articulatory parameters of training users. After selecting training users with similar articulatory parameters as the training speaker, the automatic speech recognition device may select training data associated with the selected training speakers, including parameters to use for an automatic speech recognition algorithm. By using the parameters already optimized for training users with similar articulatory parameters as the speaker, the automatic speech recognition device may quickly adapt an automatic speech recognition algorithm to the speaker.

Abstract: Dynamic security code speech-based identity authentication system and method having self-learning function, being equipped with: a time-varying data storage unit for storing speech data of each user with time labels; a time-varying data update module (23) for storing the latest speech data into the time-varying data storage unit; a time window channel construction module (24) for extracting speech data from the time-varying data storage unit in the order of the time labels, constructing and updating the time window channel comprising multiple sets of speech data; a voiceprint model reconstruction module (25) reconstructing the user voiceprint model by using the multiple sets of speech data comprised in the updated time window channel.

Abstract: A method of speaker verification comprises: comparing a test input against a model of a user's speech obtained during a process of enrolling the user; obtaining a first score from comparing the test input against the model of the user's speech; comparing the test input against a first plurality of models of speech obtained from a first plurality of other speakers respectively; obtaining a plurality of cohort scores from comparing the test input against the plurality of models of speech obtained from a plurality of other speakers; obtaining statistics describing the plurality of cohort scores; modifying said statistics to obtain adjusted statistics; normalising the first score using the adjusted statistics to obtain a normalised score; and using the normalised score for speaker verification.

Abstract: A method comprising: automatically processing recorded first sensor data from a scene to recognise automatically a first user input from user action in the scene; in response to recognition of the first user input, automatically entering a learning state to enable: automatic processing of the first sensor data from the scene to capture an ad-hoc sequence of spatial events in the scene subsequent to the first user input and automatic processing of subsequently recorded second sensor data from the scene different to the first sensor data of the scene, to recognise automatically a sequence of spatial events in the subsequently recorded second video corresponding to the captured sequence of spatial events.

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 for training a neural network of a neural network based speaker classifier for use in speaker change detection. The method comprises: a) preprocessing input speech data; b) extracting a plurality of feature frames from the preprocessed input speech data; c) normalizing the extracted feature frames of each speaker within the preprocessed input speech data with each speaker's mean and variance; d) concatenating the normalized feature frames to form overlapped longer frames having a frame length and a hop size; e) inputting the overlapped longer frames to the neural network based speaker classifier; and f) training the neural network through forward-backward propagation.

Abstract: This document describes a data processing system for processing a speech signal for voice-based profiling. The data processing system segments the speech signal into a plurality of segments, with each segment representing a portion of the speech signal. For each segment, the data processing system generates a feature vector comprising data indicative of one or more features of the portion of the speech signal represented by that segment and determines whether the feature vector comprises data indicative of one or more features with a threshold amount of confidence. For each of a subset of the generated feature vectors, the system processes data in that feature vector to generate a prediction of a value of a profile parameter and transmits an output responsive to machine executable code that generates a visual representation of the prediction of the value of the profile parameter.

Abstract: Various embodiments of the technology described herein alleviate the need to specifically request enrollment information from a user to enroll the user in a voice biometric authentication program. The system can receive voice data from a user device including audio data of a user speaking a word or phrase. The system can determine the word or phrase from the voice data to determine whether the word or phrase is in a set of available words or phrases and whether the word or phrase is usable for voice authentication of the user. In response to the word or phrase being in the set of available words or phrases and being usable for the voice authentication of the user, the system can perform authentication based on the voice data without requiring further interaction from the user.

Abstract: According to an example, correlation based instruments discovery may include extracting text from content identified as being related to instruments for implementing machine readable instructions based products. An identified content object graph model having subjects and features may be generated. A product specifications object graph model having subjects and features may be generated based upon product specifications related to a machine readable instructions based product that is to be implemented. The subjects and features in the identified content object graph model that correspond to the subjects and features in the product specifications object graph model may be correlated and scored.

Abstract: A communication support device performs communication with a plurality of terminal devices. The communication support device includes an acquirer, a changer, and a deliverer. The acquirer acquires messages from the terminal devices. The changer changes, on the acquired message, a delivery mode of the message to the delivery mode that eliminates confusion when the message has a possibility of causing the confusion. The deliverer delivers the message to the terminal devices in the delivery mode that is changed.

Abstract: A translation support system and the like are provided that is capable of preventing wasteful tasks due to simultaneous operations by more than one person and preventing inconsistent translation of translation words even in a case where a number of persons are simultaneously involved in the translation operations.

Abstract: Systems and methods for establishing communication connections using speech, such as establishing calls between speech-controlled devices, are described. A first speech-controlled device receives a communication request in the form of audio and sends audio data corresponding to the captured audio to a server. The server performs speech processing on the audio data to determine a recipient, a subject for the call, and a device associated with the recipient. The server then sends a message indicating the communication request and audio data corresponding to the communication topic to the recipient's speech-controlled device. The recipient device outputs audio to the recipient requesting whether the recipient accepts the communication request. The recipient audibly refuses or accepts the communication request, and the recipient's speech-controlled device sends an indication of the recipient's audible decision to the server.

Abstract: A computer-implemented method includes receiving a request for a verification phrase for verifying an identity of a user, and in response to receiving the request for the verification phrase, identifying subwords to be included in the verification phrase. The method also includes, in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase, based on a predetermined criteria. The method also includes providing the verification phrase as a response to the request for the verification phrase, wherein identifying subwords to be included in the verification phrase includes identifying candidate subwords, for which no stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine and from a computing device, a voice input; determining, by the dialog engine, that the received voice input is classified as feedback to an answer of a question; identifying, by the dialog engine, a predetermined feedback score associated with the feedback; and adjusting a confidence score associated with the question and the answer based on the predetermined feedback score.

Abstract: A wearable apparatus and method are provided for capturing image data. In one implementation, a wearable apparatus for capturing image data is provided. The wearable apparatus includes at least one image sensor for capturing image data of an environment of a user, wherein a field of view of the image sensor includes a chin of the user. The wearable apparatus includes two or more microphones, and an attachment mechanism configured to enable the image sensor and microphones to be worn by the user. The wearable apparatus includes a processing device programmed to capture at least one image, identify the chin of the user to obtain a location of the chin, select a microphone from the two or more microphones based on the location, process input from the selected microphone using a first processing scheme, and process input from a microphone that is not selected using a second processing scheme.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform multiple actions corresponding to this intent. The platform may select a target action to perform, and may engage in a back-and-forth dialog to obtain information for completing the target action. The action may include streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user.

Abstract: A speech recognition system, which continuously recognizes speech uttered by at least one user and controls a navigation system on the basis of a recognition result, includes: a speech-operation-intention determination unit for determining whether or not the user has made a recognized speech with the intention of operating the navigation system through speech; and a control mode altering unit for changing, when the speech-operation-intention determination unit determines that the user has no operation intention, the control mode of the navigation system in such a manner that the user is less aware of or pays less attention to the control mode than the case in which the speech-operation-intention determination unit determines that the user has an intention of operating the navigation system.

Abstract: An FFT processor applies the fast Fourier transform to each frame of an input signal and generates frequency domain data. A first spectrum calculator calculates the amplitude spectrum of the input signal for the individual frequency components based on the frequency domain data. A dispersion index calculator calculates a dispersion index indicating the level of dispersion of the amplitude spectrum of the input signal in the latest frames. A noise index calculator calculates a noise index indicating the level of noise contained in the input signal. A second spectrum calculator calculates the amplitude spectrum of the noise for the individual frequency components. A gain calculator calculates a spectral gain for suppressing the noise for the individual frequency components. An IFFT processor applies the inverse fast Fourier transform to the frequency domain data after multiplication by the spectral gain at a multiplier, and generates a signal to be output.

Abstract: System and method for analyzing audio data are provided. The audio data may be analyzed to identify speech prosody. For example, the audio data may be analyzed to select a portion of the audio data containing speech produced by a first speaker. The audio data may be further analyzed to identify speech prosody of the speech within the selected portion. Feedbacks and reports may be provided based on the identified speech prosody.

Abstract: A system and method for distinguishing the sentiment of utterances in a dialog is disclosed. The system utilizes a lexicon that is expanded from a seed using unsupervised machine learning. What results is a sentiment classifier that may be optimized for a variety of environments (e.g., conversation, chat, email, etc.), each of which may communicate sentiment differently.

Abstract: Devices, methods, and systems for voice control of components of a facility are described herein. One computing device apparatus includes a memory, and a processor configured to execute executable instructions stored in the memory to receive a voice command or voice query from a user, determine location context information associated with the computing device, and determine which component or components of the facility are associated with the voice command or voice query based, at least in part, on the location context information associated with the computing device.

Abstract: A sampled speech data sequence contains words spoken by a speaker. A sequence of feature vectors is generated characterizing spectral distribution of sampled speech data. A textual transcript of the words spoken by the speaker is obtained. Data structures of a universal background model of a Gaussian mixture model (UBM-GMM) and of an Enrolled speaker Gaussian mixture model (ENR-GMM) are adapted responsive to the textual transcript, to generate an adapted UBM-GMM and an adapted ENR-GMM, respectively. An enrolled speaker probability is generated based on the sequence of feature vectors and the adapted ENR-GMM, and a universal speaker probability is generated based on the sequence of feature vectors and the adapted UBM-GMM. A speaker verification indication of whether the speaker is an enrolled speaker is generated by comparing the enrolled speaker probability to the universal speaker probability.

Abstract: The methods, apparatus, and systems described herein are designed to reduce false positive voice print matching with fraudulent callers. A voice print of a call is created and compared to known voice prints to determine if it matches one or more of the known voice prints, and to transaction data associated with a database of voice prints. The methods include a pre-processing step to separate speech from non-speech, selecting a number of elements that affect the voice print the most, and/or generating a first score based on the number of selected audio elements matching audio elements of a voice print from the plurality of fraudulent speakers, determining if the first score exceeds a predetermined threshold score for the fraudulent speaker, and comparing the selected audio elements for the unknown caller, where the score exceeds the predetermined threshold score, to the voice prints associated with the customer account.

Abstract: Providing automatic initial responses to service requests. An automated support engine receives a service request including a problem description from a client. A text analysis component analyzes the problem description to identify an issue. A search component searches response reference sources to identify a set of suggested solutions and a set of reference materials associated with the issue. The response reference sources include structured data materials and unstructured data materials. The automated support engine combines the set of suggested solutions and a set of links corresponding to the set of reference materials to generate an automatic initial response. The automated support engine sends the automatic initial response to the client to assist a user in resolving the identified issue.

Abstract: An information processing apparatus that detects a voice command via a microphone in order to activate the device and execute certain applications. The apparatus comprises a digital signal processor (DSP) and a host controller which are responsible for processing the voice commands. The DSP recognizes and processes voice commands intermittently while the host processor is in a sleep state, thereby reducing the overall power consumption of the apparatus. Further, when the DSP is configured to recognize voice commands intended only to activate the device, a memory having a sufficiently lower storage capacity suffices.

Abstract: An engine control device is provided which includes a first fuel injection valve; a second injection valve provided at such a position that the amount of fuel injected by the second fuel injection valve and adhering to the inner peripheral wall of a cylinder is smaller; a cooling water temperature detector for detecting the temperature of cooling water for cooling an engine; and an injection ratio determining arrangement for determining the ratio between the amount of fuel injected by the first fuel injection valve and the amount of fuel injected by the second fuel injection valve based on the temperature of cooling water. The injection ratio determining arrangement stores an injection amount adjustment operation range in which the injection ratio determining arrangement is configured to increase the fuel injection ratio of the amount of fuel injected by the second fuel injection valve, when the temperature of cooling water falls.

Abstract: Disclosed is a voiceprint login method based on artificial intelligence. The method includes: S1: receiving a login request from a user and acquiring user information of the user; S2: generating a login string and replacing at least one character of the login string according to character replacement reference information corresponding to the user information; S3: providing the login string after replacement to the user and receiving speech information of the user reading the login string; and S4: performing a login authentication on the user according to speech information of the user reading the login string. With the method, by using the voiceprint authentication method combining the voiceprint and the character replacement reference information set by the user, the safety of the voiceprint password is increased, and some characters are hidden according the user's preferences, which satisfies the user's psychological demand of not wishing the password to be displayed explicitly.

Abstract: The invention relates to a method for enhanced voiceprint authentication. The method includes receiving an utterance from a user, and determining that a portion of the utterance matches a pre-determined keyword. Also, the method includes authenticating the user by comparing the portion of the utterance with a voiceprint that is associated with the pre-determined keyword. Further, the method includes identifying a resource associated with the pre-determined keyword while comparing the portion of the utterance with the voiceprint. Still yet, the method includes accessing the resource in response to authenticating the user based on the comparison.

Abstract: According to an embodiment, an utterance presentation device includes an utterance recording unit, a voice recognition unit, an association degree calculation unit, and a UI control unit. The utterance recording unit is configured to record vocal utterances. The voice recognition unit is configured to recognize the recorded utterances by voice recognition. An association degree calculation unit is configured to calculate degrees of association of the recognized utterances with a character string specified from among character strings displayed in a second display region of a user interface (UI) screen having a first display region and the second display region. A UI control unit is configured to display voice recognition results of utterances selected based on the degrees of association in the first display region of the UI screen.

Abstract: An embodiment of a method and apparatus for provisioning of a communication device includes receiving a registration request from a first communication device. The registration request includes an address associated with the first communication device. The method further includes registering the first communication device in response to receiving the registration request, placing a call request to the first communication device, and establishing a call session with the first communication device. The method further includes prompting a user of the first communication device for a user identifier, and receiving a user identifier from the user of the first communication device. The method still further includes sending one or more configuration parameters associated with the user identifier to the first communication device. The one or more configuration parameters are operable to configure the first communication device.

Abstract: An infotainment system of a vehicle includes: a primary intent module configured to determine a primary intent included in voice input using automated speech recognition (ASR); and an execution module configured to, via a first hardware output device of the vehicle, execute the primary intent. A secondary intent module is configured to: based on the primary intent, determine a first domain of the primary intent; based on the first domain of the primary intent, determine a second domain; and based on the voice input and the second domain, determine a secondary intent included in the voice input using ASR. A display control module is configured to display a request for user input indicative of whether to execute the secondary intent. The execution module is further configured to, via a second hardware output device of the vehicle, execute the secondary intent in response to user input to execute the secondary intent.

Abstract: A method, computer program product, and computer system for receiving, by a computing device, a speech signal from a speaker via a plurality of microphone zones. A temporal cue based confidence may be determined for at least a portion of the plurality of microphone zones. A power cue based confidence may be determined for at least a portion of the plurality of microphone zones. A microphone zone of the plurality of microphone zones from which to use an output signal of the speaker may be identified based upon, at least in part, a combination of the temporal cue based confidence and the power cue based confidence.

Abstract: Systems and methods for presenting location related information after a user arrives at a place. In an aspect, when a user gazes at a display of a standby device, information presentation begins. In other aspects, when a user shakes a device or says certain words to a device, and gazes at it, a presentation starts. Voice recognition techniques are used when processing voice commands.

Abstract: Embodiments are directed towards a graphical user interface identify locations within event records with splittable timestamp information. A display of event records is provided using any of a variety of formats. A splittable timestamp selector allows a user to select one or more locations within event records as having time related information that may be split across the one or more locations, including, information based on date, time of day, day of the week, or other time information. Any of a plurality of mechanisms is used to associate the selected locations with the split timestamp information, including tags, labels, or header information within the event records. In other embodiments, a separate table, list, index, or the like may be generated that associates the selected locations with the split timestamp information. The split timestamp information may be used within extraction rules for selecting subsets or the event records.