Abstract: A method whereby the date of birth (age) of a customer engaging in e-commerce over the Internet is verified. The present invention is launched from a merchant's website when an age sensitive transaction—alcohol or tobacco purchase, access to an adult web site, etc.,—is being undertaken. The system first checks to see if the customer is a known entity with a known date of birth. If the customer is not appropriately known to the system, then the system checks public records from information supplied to the system by the customer. If the date of birth is still unknown after such a check, the customer uploads an image of photo identification which is checked for date of birth either via software and also a selfie holding the identification. Optional SMS code verification can be undertaken. E-signatures can be optionally collected. Once the date of birth is known, the transaction is approved or denied based on the totality of the facts of the transaction.

Abstract: Examples of creating a device identifier that are based upon hardware components of a client device are discussed. An inaudible or high frequency reference audio sample is played. Audio capture is initiated using the microphone system. A sensor-based device identifier can be generated from the captured audio due the manufacturing variances in the hardware components used for the speaker and microphone systems.

Abstract: A computer-implemented method including forming a first user information database stored on a first server by retrieving, from a browser session, a first piece of user information including at least local user identification data and storing the first piece of user information in a user profile of the first user information database. The method further includes querying the first user information database for a second piece of user information. Responsive to not identifying the second piece of user information in the first user information database, the method further includes querying a second user information database stored on a second server for the second piece of user information associated with the first piece of user information. The method further includes retrieving the second piece of user information from the second database and saving the second piece of user information to the user profile of the first user information database.

Abstract: A dialogue system, a dialogue system control method, and an electronic apparatus are configured to process a user speech to generate a system response before the user's speech ends by recognizing the user's intention When the user's speech is finished, the system response is output to continue a natural dialogue flow in real time. The dialogue system includes: a Speech to Text engine to convert a user speech into text; an intermediate dialogue engine configured to process an intermediate speech before user speech is terminated; a final dialogue engine configured to process a final speech after the user speech is terminated; and a controller. The controller is configured to input the converted text to the intermediate dialogue engine when user speech is not terminated, and to input the converted text to the final dialogue engine when user speech is terminated The dialogue system also includes a Text to Speech engine configured to convert the system response into a speech signal.

Abstract: The present disclosure discloses a smart speaker wake-up method, a smart speaker wake-up device, a smart speaker and a storage medium, relates to the technical field of speech recognition. The method of the present disclosure is applied to a wireless network including two or more smart speakers, and a specific implementation thereof is: receiving, speech information including a wake-up word; performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word; and waking up one smart speaker in the wireless network to enter listening state according to the identification information. The present disclosure may be applied to a scenario where multiple smart speakers coexist, so as to quickly select one smart speaker that is most likely to be wakened, avoiding a chaotic speech interaction caused by multiple smart speakers being wakened simultaneously, improving efficiency and quality of speech interaction and achieving better user experience.

Abstract: A voice interaction method and a vehicle using the same are disclosed. A voice interaction method according to an embodiment of the present invention activates a personal terminal through which a voice signal of an occupant is received as a voice interaction assisting device between the vehicle and the occupant and changes presence or absence of a voice interaction between the vehicle and the occupant and voice interaction settings according to states of the vehicle and the occupant.

Abstract: A method and apparatus for processing voice data of a speech received from a speaker are provided. The method includes extracting a speaker feature vector from the voice data of the speech received from a speaker, generating a speaker feature map by positioning the extracted speaker feature vector at a specific position on a multi-dimensional vector space, forming a plurality of clusters indicating features of voices of a plurality of speakers by grouping at least one speaker feature vector positioned on the speaker feature map, and classifying the plurality of speakers according to the plurality of clusters.

Abstract: A biometric authentication system is disclosed that provides authentication capability using biometric data in connection with a challenge for parties engaging in digital communications such as digital text-oriented, interactive digital communications. End-user systems may be coupled to devices that include biometric data capture devices such as retina scanners, fingerprint recorders, cameras, microphones, ear scanners, DNA profilers, etc., so that biometric data of a communicating party may be captured and used for authentication purposes.

Abstract: A drone system is configured to capture an audio stream that includes voice commands from an operator, to process the audio stream for identification of the voice commands, and to perform operations based on the identified voice commands. The drone system can identify a particular voice stream in the audio stream as an operator voice, and perform the command recognition with respect to the operator voice to the exclusion of other voice streams present in the audio stream. The drone can include a directional camera that is automatically and continuously focused on the operator to capture a video stream usable in disambiguation of different voice streams captured by the drone.

Abstract: A system and method are disclosed for setting up a communication link between a device or application and a system with a controller. The controller can collect and send information to the application. A user interfaces with the controller to access the functionality of the application through providing commands to the controller. The system allows the user to interface with multiple applications.

Abstract: Various examples described herein are directed to systems and methods for managing an interface between a user and a user computing device. The user computing device may determine that an audio sensor in communication with the user computing device indicates a first command in a user voice of the user, where the first command instructs the user computing device to perform a first task. The user computing device may determine that the audio sensor also indicates a first ambient voice different than the user voice and match the first ambient voice to a first known voice. The user computing device may determine that a second computing device associated with the first known voice is within a threshold distance of the user computing device and select a first privacy level for the first task based at least in part on the first known voice.

Abstract: A speaker authentication method and apparatus may extract input speaker features corresponding to a plurality of frames of an input speech of an object, estimate discriminable speaker sections corresponding to the plurality of frames, and dynamically match the input speaker features to pre-enrolled enrolled speaker features based on the discriminable speaker section.

Abstract: An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a communication interface comprising communication circuitry, a memory, and a processor. The processor is configured to control the electronic apparatus to: receive a user voice for controlling an external device connected to the electronic apparatus from a user terminal through the communication interface, perform user authentication by comparing feature information obtained from the user voice with feature information pre-stored in the memory, obtain a control command for controlling the external device by analyzing the user voice based on the user being authenticated, and control the communication interface to transmit the control command to the external device.

Abstract: According to various embodiments of the disclosure, An electronic device according to various embodiments of the disclosure may include: a communication module; a display; a memory; and a processor electrically connected to the communication module, the display, and the memory, wherein the memory stores instructions that cause, when executed, the processor to: receive a voice recognition trigger command during a call while a call connection with an external electronic device is maintained; execute a voice recognition function, based on a voice received from the external electronic device; determine a function execution command corresponding to a recognized voice; and execute a function of the electronic device according to the determined function execution command.

Abstract: Systems and methods of emulating a conversation about a thematic content event are disclosed. An exemplary embodiment receives a member dialogue video from a community member who is a member of a plurality of community members, wherein the member dialogue video includes video and audio portions, and wherein the member dialogue video expresses at least one of a personal opinion and a personal viewpoint about the thematic content event; generates dialogue text from the audio portion of each received member dialogue video, wherein the dialogue text comprises words and phrases spoken by the community member in the member dialogue video; receives a modified thematic content event; compares the words and phrases of the dialogue text with the plurality of keywords; and associates at least one portion of the member dialogue video having the words and phrases of the dialogue text that match with the matching keyword of the anchor point.

Abstract: Disclosed are various embodiments for segmenting and classifying video content using sounds. In one embodiment, a plurality of segments of a video content item are generated by analyzing audio accompanying the video content item. A subset of the plurality of segments that correspond to music segments is selected based at least in part on an audio characteristic of the subset of the plurality of segments. Individual segments of the subset of the plurality of segments are processed to determine whether a classification applies to the individual segments. A list of segments of the video content item to which the classification applies is generated.

Abstract: A system for facilitating automated response to an event notifying signal, the system including a network monitoring module, an assessment module, a resource monitoring module, and a resource response module. The network monitoring module is configured for monitoring signals received over a data network for a presence of one or more event notifying signals indicative of a relevant incident. The assessment module is configured for assessing a response of the one or more event notifying signals and a resource tasked to the response. The resource monitoring module is configured for monitoring a status of a resource tasked to the response of the event notifying signal. The resource response module is configured for communicating the response to the resource tasked to the response.

Abstract: A multi-lingual speech recognition and theme-semanteme analysis method comprises steps executed by a speech recognizer: obtaining an alphabet string corresponding to a voice input signal according to a pronunciation-alphabet table, determining that the alphabet string corresponds to original words according to a multi-lingual vocabulary, and forming a sentence according to the multi-lingual vocabulary and the original words, and comprises steps executed by a sematic analyzer: according to the sentence and a theme vocabulary-semantic relationship data set, selectively executing a correction procedure to generate a corrected sentence, an analysis state determining procedure or a procedure of outputting the sentence, outputting the corrected sentence when the correction procedure successes, and executing the analysis state determining procedure to selectively output a determined result when the correction procedure fails.

Abstract: A computing device includes a processor and a memory. The processor is configured to acquire a voice instruction through at least two voice receiving devices, analyze the voice instruction to determine at least one display device controlled by the voice instruction, generate a control instruction according to the voice instruction, and send the control instruction to the at least one display device to cause the at least one display device to display corresponding contents according to the voice instruction.

Abstract: A system may support multiple tier serverless data foundation creation to support large data set processing. At a data ingestion tier, data ingestion serverless tasks may receive source data for processing. The data integration serverless tasks may filter and group the source data into file-object stored items. Further, data integration serverless tasks may capture metadata that, when paired with the file-object stored items, establishes the data foundation. The data foundation facilitates database-like performance in data operations in a database-less system. At the processing tier, the processing serverless tasks access the data foundation by iterating across the file-object stored items to generate output-object stored items. At the directed storage tier, directed storage serverless tasks capture metadata for the output-object stored items to establish an output data foundation or prepare the output data for storage in a data warehouse.

Abstract: A video camera, a computer-implemented method, and a computer-readable storage medium. The video camera including one or more microphones and a processor. The processor is configured to: acquire an output from the or each microphone; apply one or more pre-analysis filters to the or each acquired output, wherein the or each pre-analysis filter determines if the or each acquired output contains a corresponding predetermined feature of interest; and analyse the or each output, when it is determined by the or each pre-analysis filter that the corresponding output contains at least one predetermined feature of interest.

Abstract: A solution is proposed for sharing secret information for accessing a wireless computing network. A corresponding method for distributing the secret information by a source (computing) device comprises receiving a public key of the a target (computing) device, transmitting a verification token to the target device, receiving an utterance of the verification token and transmitting the secret information encrypted with the public key in response to the utterance of the verification token. A corresponding method for obtaining the secret information by a target (computing) device comprises transmitting a public key of the target device, receiving a verification token, outputting the verification token and receiving the secret information encrypted with the public key in response to an utterance of the verification token. Corresponding computer programs and computer program products are also proposed. Moreover, a source computing device and a target computing device for implementing the methods are proposed.

Abstract: A user authentication method using ultrasonic waves is disclosed. The user authentication method using ultrasonic waves, according to an embodiment of the present invention, comprises the steps of: receiving a sound wave signal which includes analog data; sampling the sound wave signal at a preset sampling rate; generating a block by selecting a preset number of pieces of sampling data; converting sampled data included in the block into frequency components; and determining, as digital data in the block, a letter or number corresponding to the frequency component having the largest magnitude from among the frequency components.

Abstract: The present disclosure proposes a solution to associate a device with a user by capturing a voice of a speaker by a microphone connected to the network device (e.g. a residential or home gateway), monitoring the IP traffic of the network device and detecting the device contributing to this IP traffic in order to establish a link between the speaker and his device(s) and associate the device with the speaker.

Abstract: A voice assistance device includes a microphone picking up and transmitting a first signal to a detection unit; the detection unit routing, in case of detection of the wakeup word in the first signal, the first signal to an analysis unit; the analysis unit processing the first signal and generating an output signal. The detection unit includes a first module detecting the wakeup word in the first signal, a second module detecting the wakeup word in a second signal received from at least one external audio source and a control module routing the first signal to the analysis unit when the wakeup word is detected solely by the first module of the detection unit.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recognizing a voice. A specific implementation of the method includes: acquiring an audio signal; determining a signal-to-noise ratio of the audio signal; and selecting a voice recognition model from a pre-trained voice recognition model group to perform voice recognition on the audio signal according to the determined signal-to-noise ratio. This embodiment improves the robustness of a voice recognition product for recognizing voices in different application scenarios.

Abstract: A system and method for improving the performance of a hands-free voice user interface system while minimizing the computational complexity without sacrificing performance. Specifically, when estimating the location of the talker for the purpose of steering a directional beam in the direction of the active talker. A hands-free voice user interface system requires a clean signal to be streamed to the cloud for recognition. One way to improve the speech signal is to estimate where the talker is and steer a beam in the direction of the active talker. To locate the talker to a localized position, a direction of arrival estimator (DOA) algorithm is used. DoA generally requires noise and echo free signal for optimal estimation, but it is computationally expensive to run audio pre-processing such as an acoustic echo cancellation for each microphone in microphone array.

Abstract: A method and apparatus for changing a talkgroup icon is provided herein. During operation a current public-safety incident is determined. Based on the current public safety incident, a talkgroup icon will be determined and pushed to the various radios that are members of the talkgroup. When a radio displays a list of talkgroups (or a single talkgroup), each talkgroup will be accompanied by the unique icon that identifies a public-safety incident related to the talkgroup. This allows a user of the radio to identify a current conversation on a particular talkgroup without having to monitor the particular talkgroup.

Abstract: A hearing device adapted to be worn by a user and for picking up sound containing the user's own voice is provided.

Abstract: An output-content control device includes a voice classifying unit configured to analyze a voice spoken by a user and acquired by a voice acquiring unit to determine whether the voice is a predetermined voice; an intention analyzing unit configured to analyze the voice acquired by the voice acquiring unit to detect intention information indicating what kind of information is wished to be acquired by the user; a notification-information acquiring unit configured to acquire notification information to be notified to the user based on the intention information; and an output-content generating unit configured to generate an output sentence as sentence data to be output to the user based on the notification information and also configured to generate the output sentence in which at least one word selected among words included in the notification information is replaced with another word when the voice is determined to be the predetermined voice.

Abstract: Hardware and/or software systems, devices, networks, and methods for identity recognition and verification based on vocal spectrum analysis. The system including one or more processors coupled to a memory/storage to collect audio samples sufficient to generate a speaker identification reference pattern and a speaker identification verification pattern, generate a speaker identification reference pattern from the audio samples and a speaker identification verification pattern from other audio samples, compare the speaker identification verification pattern with the speaker identification reference pattern; and provide a response indicating whether the speaker identification verification pattern and the speaker identification reference pattern were generated based on audio samples from the same person. The system may be employed on a mobile phone in near field communication with a control system and may include a management platform.

Abstract: Some implementations are directed to translating chatspeak to a normalized form, where the chatspeak is included in natural language input formulated by a user via a user interface input device of a computing device—such as input provided by the user to an automated assistant. The normalized form of the chatspeak may be utilized by the automated assistant in determining reply content that is responsive to the natural language input, and that reply content may be presented to the user via one or more user interface output devices of the computing device of the user. Some implementations are additionally and/or alternatively directed to providing, for presentation to a user, natural language output that includes chatspeak in lieu of a normalized form of the chatspeak, based at least in part on a “chatspeak measure” that is determined based on past usage of chatspeak by the user and/or by additional users.

Abstract: In some implementations, authentication tokens corresponding to known users of a device are stored on the device. An utterance from a speaker is received. The speaker of the utterance is classified as not a known user of the device. A query that includes the authentication tokens that correspond to known users of the device, a representation of the utterance, and an indication that the speaker was classified as not a known user of the device is provided to the server. A response to the query is received at the device and from the server based on the query.

Abstract: The present disclosure provides method and apparatus for voice forwarding in automated chatting. A first request for transmitting a voice segment may be received from a first entity in a service group. The voice segment may be received from the first entity. A voice message may be generated based on the voice segment. The voice message may be transmitted based on the first request.

Abstract: The present disclosure describes techniques for dynamically determining when information is to be output to a user, as well as what information is to be output to a user. A natural language processing system may receive, from a first device, first data representing information to be output at a first point during a skill session. The natural language processing system may also receive, from a second device, second data representing a natural language input. The natural language processing system may determine a skill component is to execute with respect to the natural language input. The natural language processing system may send, to the skill component, second data representing the natural language input. The natural language processing system may receive, from the skill component, an indication that an ongoing first skill session with the second device has reached the first point.

Abstract: Described are techniques for tracking where user sensitive data has been sent (and optionally stored). Also described are techniques for ensuring user sensitive data is deleted, from all applicable locations, in response to a user command to delete its sensitive data. In at least some embodiments, a natural language processing system may cause a skill, in communication with but not implemented by the natural language processing system, to delete sensitive data.

Abstract: A management of user profiles comprises calculating, for each speaker model of at least one speaker model, a confidence measure representing a probability that the speaker model represents a speaker of a cluster of audio segments. A user profile associated with the speaker model is updated based on a user preference assigned to the cluster of audio segments if the confidence measure calculated for the speaker model represents a probability that is higher than a target probability. The embodiments achieve an efficient user profile management in a voice-controlled context but without the need for any dedicated enrollment sessions to train speaker models.

Abstract: The present disclosure generally relates to user interfaces for managing peer-to-peer transfers. In some examples, a device provides user interfaces for initiating and managing transfers. In some examples, a device provides user interfaces corresponding to completed transfers. In some examples, a device provides user interfaces for providing visually distinguishable message object appearances based on message designation. In some examples, a device provides user interfaces for activating accounts for accepting and sending transfers. In some examples, a device provides user interfaces for exchanging accounts for use in a transfer. In some examples, a device provides user interfaces for splitting transfers between two or more accounts. In some examples, a device provides user interfaces for generating and displaying a transfers history list. In some examples, a device provides user interfaces for voice-activation of transfers.

Abstract: Briefly, a portable intelligent device is provided that has an audio input for receiving a voice input from a user and an event manager for detecting that an event has occurred. The intelligent device also stores a passcode and a voice-code indicative of the passcode that is unique to a particular user. The intelligent device presents the passcode to a user, for example, from a display on the device, or from smart phone or tablet wirelessly connected to the intelligent device. The user speaks the passcode into an input transducer (microphone) on the intelligent device, and a processor generates a voiceprint that reflects the spoken passcode. The processor then can use the stored voice-code and the generated voiceprint to determine if a specific user was speaking, and if the user spoke the correct passcode. In this way the intelligent device is able to authenticate or authorize a remote user simply by having the user anonymously speak a passcode into the intelligent device.

Abstract: Examples of the present disclosure describe systems and methods for detecting monotone speech. In aspects, audio data provided by a user may be received a device. Pitch values may be calculated and/or extracted from the audio data. The non-zero pitch values may be divided into clusters. For each cluster, a Pitch Variation Quotient (PVQ) value may be calculated. The weighted average of PVQ values across the clusters may be calculated and compared to a threshold for determining monotone speech. Based on the comparison, the audio data may be classified as monotone or non-monotone and an indication of the classification may be provided to the user in real-time via a user interface. Upon the completion of the audio session in which the audio data is received, feedback for the audio data may be provided to the user via the user interface.

Abstract: An electronic apparatus is provided. The electronic apparatus includes an inputter comprising input circuitry, a voice receiver comprising voice receiving circuitry, a storage, and a processor configured to: provide a guide prompting a user utterance based on user authentication being performed according to user information input through the inputter, generate a speaker recognition model corresponding to the user information based on a voice corresponding to the guide being received through the voice receiver, store the speaker recognition model in the storage, and identify a user corresponding to a voice received through the voice receiver based on the speaker recognition model updated by comparing a voice received through the voice receiver with the speaker recognition model.

Abstract: In one aspect, a playback device includes a voice assistant service (VAS) wake-word engine and a command keyword engine. The playback device detects, via the command keyword engine, a first command keyword of in voice input of sound detected by one or more microphones of the playback device. The playback device determines an intent based on at least one keyword in the voice input via a local natural language unit (NLU). After detecting the first command keyword event and determining the intent, the playback device performs a first playback command corresponding to the first command keyword and according to the determined intent. When the playback device detects, via the wake-word engine, a wake-word in voice input, the playback device streams sound data corresponding to at least a portion of the voice input to one or more remote servers associated with the VAS.

Abstract: The present disclosure is generally directed a data processing system for authenticating packetized audio signals in a voice activated computer network environment. The data processing system can improve the efficiency and effectiveness of auditory data packet transmission over one or more computer networks by, for example, disabling malicious transmissions prior to their transmission across the network. The present solution can also improve computational efficiency by disabling remote computer processes possibly affected by or caused by the malicious audio signal transmissions. By disabling the transmission of malicious audio signals, the system can reduce bandwidth utilization by not transmitting the data packets carrying the malicious audio signal across the networks.

Abstract: Systems and methods for contextual search query revision are disclosed. A user utterance including at least one semantic component is received and a plurality of candidate n-grams including the at least one semantic component and at least one additional semantic component selected from a set of prior semantic components is generated. A probability that each of the plurality of candidate n-grams is an intended n-gram is calculated and a selected one of the plurality of candidate n-grams is output based on the probability.

Abstract: A system for audio control in a vehicle includes a speaker designed to output vehicle audio data in a cabin of the vehicle at a volume. The system further includes a microphone designed to detect microphone data in the cabin of the vehicle. The system further includes a memory designed to store an audio profile corresponding to desirable operation of the volume of the speaker. The system also includes an electronic control unit (ECU) coupled to the speaker, the microphone, and the memory and designed to control the volume of the speaker based on the detected microphone data and the audio profile.

Abstract: A voice data processing method includes acquiring historical voice data, acquiring historical voice feature vectors corresponding to the historical voice data, and performing clustering on the historical voice feature vectors to obtain a voice feature cluster, the voice feature cluster comprising at least one historical voice feature vector with a similar feature. The method also includes, when the voice feature cluster matches a high-frequency user condition, training a corresponding user voice model according to the historical voice feature vectors contained in the voice feature cluster; after a current voice feature vector of the current voice data matches the user voice model, initiating a user identity association request associated with the current voice data; and, after a response message corresponding to the user identity association request is received, binding user identity information in the response message to the user voice model.

Abstract: An electronic device and method are disclosed herein. The electronic device includes a speaker, microphone, processor and memory storing instructions, which implement the method, including: determining whether registration of a first user is required based on a first voice signal obtained through a microphone of the electronic device, when registration of the first user is required, requesting authentication of the first user by a second user preregistered at the electronic device, and when information authenticating the first user by the second user is received, registering the first user based on the received information.

Abstract: A fixed-wing aircraft advertisement method, system, and non-transitory computer readable medium for a fixed-wing aircraft, include advertising from samples of speech heard by the fixed-wing aircraft at a given location.

Abstract: A face image retrieval method includes: obtaining to-be-retrieved face information corresponding to a to-be-retrieved image by a convolutional neural network, the convolutional neural network being configured with corresponding convolution calculation configuration information by a processor, the convolutional neural network including at least one convolutional layer, the convolution calculation configuration information including a data bit width value corresponding to each convolutional layer in the convolutional neural network, and the to-be-retrieved image including at least one face region; searching a database for matched preset face image information that matches the to-be-retrieved face information, the database storing at least one piece of preset face image information; and outputting the preset face image information that matches the to-be-retrieved face information.

Abstract: The invention provides systems, methods and computer program products for secure electronic payment transactions based on voice generated currency tokens. The invention comprises implementing at a voice currency platform server, the steps of (i) receiving from a payor terminal device a request for generation of a voice currency token, (ii) performing voice based biometric authentication by matching the voice data received from the payor terminal device against one or more voice based biometric templates associated with the payor voice currency platform account, (iii) performing speech analysis to extract at least the currency amount identified within the voice data received from the payor terminal device and (iv) generating an encrypted voice currency token.