Abstract: Disclosed are an artificial intelligence-based method and device for voiceprint authentication. The method comprises receiving a registration request of a user and providing a registration string to the user; receiving voice information of the user reading the registration string and producing N segments of voice on the basis of the voice information, where N is a positive integer; determining a gender tag of the user on the basis of a gender classification model and the N segments of voice; and producing a registration voiceprint model for the user on the basis of the gender tag and the N segments of voice.

Abstract: A computer-implemented method for authenticating speech includes executing on a computer processor the step of receiving speech and context for the speech of a speaker, wherein the speech is received as electronic voice communication, wherein the context for the speech includes biometric information measured during the received speech. The speaker is authenticated according the received speech and the context by a speech with context model. A result of the authentication is returned.

Abstract: A computer-implemented method for detecting anomalous behavior of one or more computers in a large group of computers comprises (1) receiving log files including a plurality of entries of data regarding connections between a plurality of computers belonging to an organization and a plurality of websites outside the organization, each entry being associated with the actions of one computer, (2) applying a first plurality of algorithms to determine features of the data which may contribute to anomalous behavior of the computers, and (3) applying a second plurality of algorithms to determine which computers are behaving anomalously based upon the features.

Abstract: An embodiment provides a system (100) and a method (700) for enabling translation of speech is provided. The system includes an application module (104) configured to receive input identifying a first language of an audio input and a second language into which the audio input in the first language is to be translated. The application module (104) determines the availability of at least one human translator capable of translating the first language into the second language and second language into the first language, in at least one database of human translator. Content, in the second language, which has been translated using the audio input in the first language, is received by the application module (104) from the available human translator. Machine translated content in the second language is received by the application module (104) if the at least one human translator is unavailable.

Abstract: An audio firewall system has a microphone that generates audio data. A speech-to-text engine converts the audio data to text data. The text data is parsed for a service wake word and corresponding content data. The service wake word identifies one of a local security system and a remote assistant server. A text-to-speech engine converts the service wake word and the corresponding content data to converted audio data. The converted audio data is provided to the remote assistant server. The content data is provided to the local security system. The audio firewall system receives a response from the remote assistant server or the local security system and outputs an audio signal corresponding to the response.

Abstract: This invention provides a means to identify unknown media programming using the audio component of said programming. The invention extracts audio information from the media received by consumer electronic devices such as smart TVs and TV set-top boxes then conveys said information to a remote server means which will in turn identify said audio information of unknown identity by way of testing against a database of known audio segment information. The system identifies unknown media programming in real-time such that time-sensitive services may be offered such as interactive television applications providing contextually related information or television advertisement substitution. Other uses include tracking media consumption among many other services.

Abstract: Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

Abstract: An authentication apparatus in a multifunction peripheral is configured to display, in a screen, an account field and a password field so as to allow an input, inhibit an input in the account field before an input is made in the password field, mask a letter inputted in the password field, and restrict a letter string including a same letter that has been inputted in the password field, from being inputted in the account field.

Abstract: A computer-implemented method for speech diarization is described. The method comprises determining temporal positions of separate faces in a video using face detection and clustering. Voice features are detected in the speech sections of the video. The method further includes generating a correlation between the determined separate faces and separate voices based at least on the temporal positions of the separate faces and the separate voices in the video. This correlation is stored in a content store with the video.

Abstract: A voice assistant system may be configured to receive a spoken introduction from a trusted user to introduce a new user and designate access privileges for the new user. The voice assistant system may process the speech using automated speech recognition and may parse the text to determine intent. The voice assistant system may also analyze the speech to determine a profile associated with the speaker that spoke the introduction. The voice assistant system may determine that the trusted user includes administrative privileges. The access privileges, when granted, may allow the new user to interact with the voice assistant system, such as to issue commands, extract information, play media, and/or perform other actions with the voice assistant system, which may be unavailable to people who are not introduced to the voice assistant system by a trusted user and/or do not have the access privileges associated with a user profile.

Abstract: User input into a user interface is symbolically represented to increase security. User input received into a user interface and a mapping is applied to the user input. A result of the mapping is provided. The user interface may be updated to include the result of the mapping and/or may be provided to another device, such as over a short range communication channel. A person who views or otherwise has access to the user interface does not obtain the user input, but the result of the mapping indicates whether the user input was provided correctly.

Abstract: The present invention provides a method, apparatus, and system for voice verification, wherein the method comprises: at a network side, obtaining a user voice communication number according to a voice verification request from a user side, and determining voice verification information corresponding to the voice verification request; at the network side, initiating a call to a corresponding user according to the user voice communication number, and in the case of call through, playing the determined voice verification information to the user; at the user side, performing an automatic listening and recording operation when monitoring that the user is called, and upon termination of the call, sending recording information obtained from the recording to the network side; at the network side, determining a verification result according to the voice verification information and the recording information.

Abstract: A head-mounted device (HMD) that includes at least one speaker, at least one audio capturing device and circuitry is provided. The circuitry receives, via the at least one audio capturing device, a user input that corresponds to an audio input. The circuitry further determines a first location of a source of the received audio input, based on the received audio input. The circuitry further determines that the received audio input is enunciated from a wearer of the HMD in a worn state of the HMD, based on the determined first location of the source of the received audio input. The circuitry further controls at least a function of the HMD, based on the determination that the received audio input is enunciated from the wearer.

Abstract: Systems and methods for visual processing of spectrograms to generate haptic effects are disclosed. In one embodiment, a signal comprising at least an audio signal is received. One or more spectrograms may be generated based at least in part on the received signal. One or more haptic effects may be determined based at least in part on the spectrogram. For example, a generated spectrogram may be a two-dimensional image and this image can be analyzed to determine one or more haptic effects. Once a haptic effect has been determined, one or more haptic output signals can be generated. A generated haptic output signal may be output to one or more haptic output devices.

Abstract: The invention is directed to combining web browser and audio player functionality for the organization and consumption of web documents. Specifically, the invention identifies a set of web documents via a web browser, extracts content from the web documents, and adds the set of web documents to a playlist. In this way, users can build a playlist of web documents and utilize the functionality and convenience of an audio player and listen to the content of the playlist.

Abstract: A restricted access device such as a cellphone, a tablet or a personal computer, analyzes contemporaneous keyboard inputs of a password and gestures to authenticate the user and enable further access to applications and processes of the restricted access device. The gestures may be facial gestures detected by a camera or may be gestures made by an avatar rendered on a display of the device. The password may be shorted based upon the context of the authentication as well as any gestures occurring during password entry. The gestures may be learned by the restricted access device during the password entry process.

Abstract: A restricted access device such as a cellphone, a tablet or a personal computer, analyzes contemporaneous keyboard inputs of a password and gestures to authenticate the user and enable further access to applications and processes of the restricted access device. The gestures may be facial gestures detected by a camera or may be gestures made by an avatar rendered on a display of the device. The password may be shorted based upon the context of the authentication as well as any gestures occurring during password entry. The gestures may be learned by the restricted access device during the password entry process.

Abstract: A restricted access device such as a cellphone, a tablet or a personal computer, analyzes contemporaneous keyboard inputs of a password and gestures to authenticate the user and enable further access to applications and processes of the restricted access device. The gestures may be facial gestures detected by a camera or may be gestures made by an avatar rendered on a display of the device. The password may be shorted based upon the context of the authentication as well as any gestures occurring during password entry. The gestures may be learned by the restricted access device during the password entry process.

Abstract: A third party verification system, comprising a response unit in communication with at least a first party, said response unit configured to elicit information in the form of a response from the at least first party, and a voice print server in communication with said response unit, said voice print server configured to receive and store said information to provide a record for third party verification that the at least first party consented to enter into the at least one transaction with the at least one second party.

Abstract: A method enhances an emergency reporting system for controlling equipment. A message receiver receives an electronic message from a person. The electronic message is a report regarding an emergency event. One or more processors identify a profile of the person who sent the electronic message, and determine a bias of the person regarding the emergency event based on the person's profile. One or more processors amend, based on the bias of the person, a content of the electronic message to create a modified electronic message regarding the emergency event. The modified electronic message is consolidated with other modified electronic messages into a bias-corrected report about the emergency event. One or more processors then automatically adjust equipment based on the bias-corrected report about the emergency event.

Abstract: In some implementations, (i) audio data representing a voice command spoken by a speaker and (ii) a speaker identification result indicating that the voice command was spoken by the speaker are obtained. A voice action is selected based at least on a transcription of the audio data. A service provider corresponding to the selected voice action is selected from among a plurality of different service providers. One or more input data types that the selected service provider uses to perform authentication for the selected voice action are identified. A request to perform the selected voice action and (i) one or more values that correspond to the identified one or more input data types are provided to the service provider.

Abstract: An information security method operable to be executed in an electronic device with modules, such as a calculating module, a first determining module, an extracting module, a logic operation module, and an adjusting module. The modules find out audio segments which are suitable for the concealing of copyright and other information by way of phase inversion of the original data as audio codecs are applied and build the concealable information into the data by way of a key.

Abstract: Obtaining and/or validating user credentials at client devices is described. A phrase may be generated based on one or more index values determined according to a function of time and a credential identifier identifying a user credential. The phrase may be output by the client device for validating the user credential.

Abstract: A system to control turning on an engine of a vehicle includes a relay and a detect circuit. The detect circuit is configured to detect a client device and, upon detection of a client device, to assert a signal indicating that a client device has been detected. Responsive to detection of the client device, the detect circuit generates a signal to cause the relay to close upon activation of a starter control in the vehicle to thereby cause current to flow to a starter motor in the vehicle.

Abstract: An alcohol consumption determination method includes detecting a plurality of effective frames of an input voice signal; detecting a difference in signal of within the original signal of each of the effective frames; detecting average energy of the original signal and average energy of the difference signal for each of the effective frames; and determining whether alcohol has been consumed based on a difference between the average energy of the original signal and the average energy of the difference between the signals for each effective frame. Accordingly, it is also possible to determine, from a remote location, whether a driver or an operator remote has consumed alcohol and the degree of inebriation by using a difference signal energy method using a voice signal, thus preventing an accident caused by a operation vehicles and machines under the influence of alcohol.

Abstract: An alcohol consumption determination method includes: detecting an effective frame of an input voice signal; detecting a difference signal of an original signal of the effective frame; performing fast Fourier conversion on the original signal and the difference signal; and determining, in the frequency domain, whether alcohol has been consumed based on a slope difference between the fast-Fourier-transformed original signal and the fast-Fourier-transformed difference signal. Accordingly, it is also possible to determine whether a driver or an operator from a remote location has consumed alcohol and a degree of the consumption, thus preventing an accident caused by an individual operating a vehicle under the influence.

Abstract: Provided is a speech recognition system, including: a first information processing device including a speech recognition processing unit for receiving data to be used for speech recognition transmitted via a network, carrying out speech recognition processing, and returning resultant data; and a second information processing device connected to the first information processing device via the network. The second information processing device performs conversion of the data into data having a format that disables a content thereof from being perceived by application of a mapping function on phoneme ID's associated with the content, and also enables the speech recognition processing unit to perform the speech recognition processing.

Abstract: A method for recording conversation is provided. The method includes capturing content, receiving at least one voice signal, distinguishing at least one person corresponding to the at least one voice signal by analyzing the at least one voice signal, converting the at least one voice signal into a text corresponding to the at least one voice signal, and displaying the text in the captured content to correspond to the distinguished at least one person.

Abstract: A method at a first electronic device of multiple electronic devices, each electronic device of the plurality of electronic devices including one or more microphones and a speaker, includes detecting a voice input; determining a quality score for the detected voice input; communicating the quality score to the other devices of the plurality of electronic devices; receiving quality scores generated by the other devices for detection of the voice input by the other devices; if the quality score generated by the first electronic device is the highest amongst the quality scores, outputting an audible and/or visual response to the detected voice input, where the other devices of the plurality of electronic devices forgo outputting an audible response to the detected voice input; and if the quality score generated by the first electronic device is not the highest amongst the quality scores, forgoing outputting a response to the detected voice input.

Abstract: An anti-distracted driver system comprises an interrupt device and a client device detector. The system may be installed in a vehicle. The client device detector may be installed in, for example, the glove box and may detect whether a client device (e.g., smart phone) is present (also in the glove box). If a client device is detected, an identifier (ID) is extracted from the client device and compared to a set of valid client device IDs provided by an administrator. If no match is found or no client device is detected, a relay is, or remains, disengaged thereby electrically disconnecting the starter control (e.g., ignition switch) from a solenoid of the starter motor thereby preventing the vehicle's engine from being started. Thus, the engine cannot be started unless the vehicle operator places his or her phone in the glove box of the vehicle (or wherever the client device detector is otherwise located).

Abstract: There is provided a method for producing a customized content, comprising identifying a customizable content from which to produce the customized content, identifying a base content in the customizable content, and receiving at least one customizing criterion as input. The method further comprises determining a plurality of content modifiers for harmonizing the base content and the customizing criterion, extracting the plurality of content modifiers from a modification library, and integrating the plurality of content modifiers with the base content to produce the customized content. In one embodiment, the method is embodied as instructions stored on a computer-readable medium. A system for producing customized content comprises a content host hosting a customizable content including a base content, a modification library, and a content customizing application.

Abstract: A method including generating respective audio signals from microphones of an apparatus; determining which camera(s) of a plurality of cameras of the apparatus has been selected for use; and based upon the determined camera(s) selected for use, selecting an audio processing mode for at least one of the respective audio signals to be processed, where the audio processing mode at least partially automatically adjusts the at least one respective audio signals based upon the determined camera(s) selected for use.

Abstract: Systems and methods for detecting a synchronization code word embedded in a plurality of frames of a signal are described. In one example embodiment, the synchronization code word contains “s” bits, embedded one bit per frame in “s” frames of an input signal. The method of detecting this synchronization code word includes: initiating a first segmentation procedure wherein “n” segments are defined in each signal frame of the input signal. A first correlation threshold value, which is based on the synchronization code word, is used to identify in the “n” segments, a first segment having the highest likelihood of containing at least a portion of the synchronization code word. The first segment is used to initiate a recursive detection procedure incorporating one or more additional segmentation procedures and one or more additional correlation threshold values, to detect the synchronization code word in a sub-divided portion of the first segment.

Abstract: A system and methodology that provides a network-based, e.g., cloud-based, background expert for predicting and/or accomplishing a user's goals is disclosed herein. Moreover, the system monitors, in the background, user generated data and/or publicly available data to determine and/or infer a user's goal, with or without an active indication/request from the user. Typically, the user-generated data can include user conversations, such as, but not limited to, speech data in a voice call, text messages, chat dialogs, etc. Further, the system identifies an action or task that facilitates accomplishment of the user goal in real-time. Moreover, the system can automatically perform the action/task and/or request user authorization prior to performing the action/task.

Abstract: Voice print identification for identifying speakers at an event is provided. A plurality of speakers at an event are recorded and associated with identity indicators. Voice prints for each speaker are associated with each of the plurality of recorded speakers. Determining based on the event, the list of attendees for the event, and the identity indicators, whether the voice print for at least one speaker corresponds to a known.

Abstract: A device may determine that a user device should be authenticated; and determine a confidence measurement based on an established activity pattern of the user device. The confidence measurement may relate to a likelihood that an authorized user of the user device is in possession of the user device. The device may authenticate the user device based on the confidence measurement.

Abstract: Systems, computer-implemented methods, and tangible computer-readable media are provided for voice authentication. The method includes receiving a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource, pre-authenticating the speech sample, transmitting an authentication request to an authentication server, which compares the speech sample to a previously established speech profile associated with the user, and providing access to the restricted access resource based on the response.

Abstract: Systems and methods are provided for unlocking remote devices using a biometric input that is associated with a code stored on a mobile electronic device. After validating a biometric input that corresponds with a code that locks or unlocks a remote lock, the code may be sent to a remote electronic device in a transmission. When the code is validated by the remote electronic device as being associated with unlocking the remote lock, the remote device may then unlock the lock.

Abstract: A method for verifying and identifying users, and for verifying users' identity, by means of an authentication device capable of transmitting, receiving and recording audio or ultrasonic signals, and capable of converting the signals into digital data, and performing digital signal processing. Voice pattern(s) and user(s) information of one or more authorized user(s) are recorded and stored on the authentication device. User(s) identification is verified by inputting to the authentication device a vocal identification signal from a user, and comparing the voice pattern of the vocal identification signal with the recorded voice pattern(s) of the authorized user(s), and if a match is detected issuing an indication that the user is identified as an authorized user.

Abstract: A method for tracking the location of an individual can include selecting a first audio clip from a plurality of audio clips, wherein each audio clip comprises a different question for the individual and wherein a correct answer corresponds to each audio clip. The method can further include initiating a telephone call to a telephone of the individual at a desired location and playing the first audio clip for the individual via the telephone call. The method can further include receiving an oral response to the first audio clip from the individual via the telephone call and executing a speech recognition process upon the oral response. The method can further include comparing the oral response to a voice print of the individual and storing a record indicating that the individual is compliant if the oral response matches the correct answer and the oral response matches the voice print.

Abstract: A computer-implemented method to execute anti-theft procedures for a device is described. Receipt of a first audio file is detected. The first audio file is converted to a first text file. The first text file is analyzed to identify an anti-theft command. The anti-theft command is executed based at least in part on the analysis.

Abstract: Certain aspects of an apparatus and method for scene change detection-based trigger for audio fingerprinting analysis may include a content-rendering device communicably coupled to a content-server. The content-rendering device may sample an audio component of the content at a sampling rate. The content-rendering device may generate and communicate to the content-server, an audio fingerprint based on the sampled audio component. The content-rendering device may further modify the sampling rate based on a detected scene change in the content. The scene change may be detected based on the communicated audio fingerprint. In another embodiment, the content-server may receive a plurality of audio fingerprints and detect a change in a type of content associated with the plurality of audio fingerprints. The content-server may further communicate a trigger signal to the content-rendering device that indicates the detected change in the type of content associated with the plurality of audio fingerprints.

Abstract: Disclosed herein are systems, computer-implemented methods, and computer-readable storage media for generating personalized user models. The method includes receiving automatic speech recognition (ASR) output of speech interactions with a user, receiving an ASR transcription error model characterizing how ASR transcription errors are made, generating guesses of a true transcription and a user model via an expectation maximization (EM) algorithm based on the error model and the respective ASR output where the guesses will converge to a personalized user model which maximizes the likelihood of the ASR output. The ASR output can be unlabeled. The method can include casting speech interactions as a dynamic Bayesian network with four variables: (s), (u), (r), (m), and encoding relationships between (s), (u), (r), (m) as conditional probability tables. At each dialog turn (r) and (m) are known and (s) and (u) are hidden.

Abstract: Exchanging information via a designated application includes establishing a voice communication link with a client device, sending a launch command associated with a designated application to the client device via the voice communication link, wherein the launch command is configured to cause the designated application to be launched at the client device; and exchanging information with the client device using the designated application, wherein the designated application is configured to receive input information and the input information is received from the client device.

Abstract: A telephone device and a method and for controlling a mute function in the telephone device. While the mute function is active, voice recognition software in the telephone device processes sound detected by a microphone in the telephone device to recognize and identify one or more specific words as having been spoken by a specific person and not by another person, and in response, the telephone device activates an alarm in the telephone device to communicate that the mute function is active. The voice recognition software was trained, prior to the sound having been detected, to differentiate the one or more specific words spoken by the specific person from the same one or more specific words spoken by other people.

Abstract: Systems and methods are provided herein relating to audio matching. The density and quality of interest points can be controlled to assure a small but uniform number of high quality interest points. By scoring interest points based on quality and comparing them over time, those interest points that maintain a high quality when compared with a varying number of neighboring interest points can be retained, while those interest points that do not maintain a high quality can be discarded. Thus, the scalability of an audio matching system can be improved while retaining accuracy.

Abstract: Provided are an audio encoding method and apparatus and an audio decoding method and apparatus in which audio signals can be encoded or decoded so that sound images can be localized at any desired position for each object audio signal. The audio decoding method generating a third downmix signal by combining a first downmix signal extracted from a first audio signal and a second downmix signal extracted from a second audio signal; generating third object-based side information by combining first object-based side information extracted from the first audio signal and second object-based side information extracted from the second audio signal; converting the third object-based side information into channel-based side information; and generating a multi-channel audio signal using the third downmix signal and the channel-based side information.

Abstract: Systems and methods are provided herein relating to audio matching. In addition to interest points, localized patches surrounding interest points can be used as additional discriminative information. The patches can be compressed to increase scalability while retaining discriminative information related to the localized region within the patch. Compressed patches related to interest points of an audio sample can be compared to compressed patches related to interest points of a reference sample to determine whether the two samples are a match.

Abstract: Methods and apparatus to perform audio watermark detection and extraction are disclosed. An example method includes sampling a media signal to generate samples, wherein the media signal includes an embedded message, determining a first symbol value for a first block of the samples, determining a second symbol value for a second block of the samples, and determining, using a processor, a resulting symbol value, representative of a part of the embedded message, based on the first symbol value and the second symbol value for the first block of samples and the second block of samples, wherein the first block and the second block partially overlap.

Abstract: A computer-implemented method of determining when an audio notification should be generated includes detecting receipt of a triggering event that occurs on a user device; generating, based on detecting, the audio notification for the triggering event; receiving, from the user device, a user voice command responding to the audio notification; and generating a response to the user voice command based on one or more of (i) information associated with the audio notification, and (ii) information associated with the user voice command.