Abstract: Managing the delivery of a presentation in real-time includes receiving a presentation including a plurality of slides, wherein each slide of the plurality of slides is allocated an amount of time for display during delivery of the presentation and is associated with a slide subject, determining subjects of interest for an audience of the presentation from a social media website, and correlating, using a processor, the subjects of interest with the plurality of slides of the presentation. A recommendation is generated using the processor. The recommendation specifies a modification to the presentation according to the correlation of subjects of interest with the plurality of slides of the presentation. Further, the recommendation is indicated using a display.

Abstract: A method for determining a voice command shortcut includes receiving a first voice command providing instructions for performing a particular task and a second voice command providing additional instructions for performing the same task. The voice command shortcut may be used in place of the first and second voice commands, which are typically submitted in response to system prompts. The availability of a voice command shortcut is determined based on the first and second voice commands. If a voice command shortcut is available, an audible and/or visual notification may be provided to inform the user of the available voice command shortcut.

Abstract: A video stream from a webcam or video telephone is received. The video stream can be analyzed in real-time as it is being received or can be recorded and stored for later analysis. Information within the video streams can be extracted and processed by a facial and video content recognition engine and the information derived therefrom can be stored as metadata. The metadata can be used for enriching the call content recorded by a recorder. The information derived from the video streams can be used to solve business and legal issues.

Abstract: Devices, methods, and systems for detecting wake words and audio commands that should be disregarded are disclosed. In some instances, a local device may receive a wake word or audible command transmitted or uttered in a television or radio advertisement, program, broadcast, etc. In these instances, the local device should disregard such wake words and audible commands, as they are not from a user of the local device. To detect such wake words and commands, audio fingerprinting and speech recognition techniques may be used to determine whether the wake word and/or command substantially matches the audio of a known television or radio advertisement, program, broadcast, etc. If the wake word and/or command substantially matches, the local device may then disregard the command.

Abstract: Methods and systems for enrolling a user in an authentication program. In some embodiments, voice interaction that includes a request or command is received from a user. The user may be requested to provide authentication information to fulfill the request or command made during the voice interaction. The user may be authenticated using a first authentication method. The user may be passively enrolled into an authentication program that uses a second authentication method. Enrolling may include deriving characteristics of the user's voice from the voice interaction. After the user is enrolled in the authentication program, the second authentication method may be used to authenticate the user prior to fulfilling requests or commands made during voice navigation.

Abstract: A speaker change detection device sets first and second analysis periods before and after each of time points in a voice signal, generates, for each of the time points, a first speaker model from a distribution of features in frames in the first analysis period, and a second speaker model from a distribution of features in frames in the second analysis period, calculates, for each of the time points, a matching score representing the likelihood of similarity of features between a group of speakers in the first analysis period and a group of speakers in the second analysis period by applying the features extracted from the second analysis period to the first speaker model and applying the features extracted from the first analysis period to the second speaker model, and detects a speaker change point on the basis of the matching scores at the plurality of time points.

Abstract: Methods and systems of text independent speaker recognition provide a complexity comparable to text dependent speaker recognition system. These methods and systems exploit the fact that speech is a quasi-stationary signal and simplify the recognition process based on this theory. The speaker modeling allows a speaker profile to be updated progressively with new speech samples that are acquired during usage over time by the speaker.

Abstract: Techniques described herein are directed to the enhancement of spectral features of an audio signal via adaptive modulation filtering. The adaptive modulation filtering process is based on observed modulation envelope autocorrelation coefficients obtained from the audio signal. The modulation envelope autocorrelation coefficients are used to determine parameters of an adaptive filter configured to filter the spectral features of the audio signal to provide filtered spectral features. The parameters are updated based on the observed modulation envelope autocorrelation coefficients to adapt to changing acoustic conditions, such as signal-to-noise ratio (SNR) or reverberation time. Accordingly, such acoustic conditions are not required to be estimated explicitly. Techniques described herein also allow for the estimation of useful side information, e.g.

Abstract: Provided are techniques for voice focus enabled by predetermined triggers. Voice recognition is used to identify one or more pre-determined triggers from a voice of a speaker. In response to identifying the one or more pre-determined triggers, a voice recognition template is dynamically created for the voice of the speaker, and the voice recognition template and voice isolation are used to focus on the voice from the speaker.

Abstract: Provided are techniques for voice focus enabled by predetermined triggers. Voice recognition is used to identify one or more pre-determined triggers from a voice of a speaker. In response to identifying the one or more pre-determined triggers, a voice recognition template is dynamically created for the voice of the speaker, and the voice recognition template and voice isolation are used to focus on the voice from the speaker.

Abstract: A system is configured to execute audio-initiated commands. The system detects audio and determines if a first sound is included in the audio. The system then processes further incoming audio to detect a second sound. If the second sound is not detected within a time threshold, the system executes a command. The command may include delivering a message, outputting audio corresponding to synthesized speech, or some other executable command.

Abstract: A method for enhancing the accuracy performance of authentication systems includes determining an authentication data requirement for a desired transaction and at least one new verification phrase. The method also includes capturing authentication data from a user with a communications device in accordance with the authentication data requirement, and capturing biometric data of the at least one new verification phrase from the user with the communications device. Moreover, the method includes adding the determined at least one new verification phrase to an enrollment phrase registry and storing the biometric data captured for the at least one new verification phrase in an enrollment data record of the user after successfully authenticating the user.

Abstract: Embodiments of techniques or systems for fraud detection are provided herein. A communication may be received where the communication includes one or more voice signals from an individual. Frequency responses associated with these voice signals may be determined and analyzed and utilized to determine whether or not potential fraudulent activity is occurring. For example, if a frequency response is greater than a frequency threshold, potential fraudulent activity may be determined. Further, frequency responses may be cross referenced with voice biometrics, voice printing, or fraud pathway detection results. In this way, voice stress or frequency responses may be utilized to build other databases related to other types of fraud detection, thereby enhancing one or more aspects of fraud detection. For example, a database may include a voice library, a pathway library, or a frequency library which include characteristics associated with fraudulent activity, thereby facilitating identification of such activity.

Abstract: A method and associated system and computer program product. A sample of speech, for which a source of the sample of speech is to be classified, is received. A frequency clip level of the sample of speech is determined. A higher frequency clip level indicates the source is human and a lower frequency clip level indicates the source is machine generated. A dynamic range of the sample of speech is determined. A lower dynamic range indicates the source is human and a higher dynamic range indicates the source is machine generated. The frequency clip level and the dynamic range are weighted by a respective weighting factor as to whether the source is human or the source is machine generated. The source is classified as human generated or machine generated. The classifying of the source is based on the frequency clip level, the dynamic range, and the respective weighting factors thereof.

Abstract: Techniques for using both speaker-identification information and other characteristics associated with received voice commands to determine how and whether to respond to the received voice commands. A user may interact with a device through speech by providing voice commands. After beginning an interaction with the user, the device may detect subsequent speech, which may originate from the user, from another user, or from another source. The device may then use speaker-identification information and other characteristics associated with the speech to attempt to determine whether or not the user interacting with the device uttered the speech. The device may then interpret the speech as a valid voice command and may perform a corresponding operation in response to determining that the user did indeed utter the speech. If the device determines that the user did not utter the speech, however, then the device may refrain from taking action on the speech.

Abstract: Some embodiments include a method for gesture based search. Other embodiments of related methods and systems are also disclosed.

Abstract: Disclosed embodiments enable improved perception of a user's response and/or preferences. Search results responsive to a query are presented to the user. Parameters associated with an implicit user response are tracked. The implicit response may consist of a delay from the presentation of the user response; a speed of, a volume of, a tone of, or a word used in a user response; a speed, a direction, and/or a consistency of a pointer movement; a location of a touch; a change in a touch; and/or a user movement captured by a camera. Measurements and other information derived from the tracked parameters may be stored in a user profile, which may later be used to calculate a personalized implicit response. An implicit response may be calculated from the parameters. The implicit response may be used to qualify an explicit response, which may be the impetus to modify search results.

Abstract: Devices, methods, systems, and computer-readable media for adaptive beam forming are described herein. One or more embodiments include a method for adaptive beam forming, comprising: receiving a voice command at a number of microphones, determining an instruction based on the received voice command, calculating a confidence level of the determined instruction, determining feedback based on the confidence level of the determined instruction, and altering a beam of the number of microphones based on the feedback.

Abstract: Waveform display control techniques of visual characteristics are described. In one or more examples, a method is described of increasing user efficiency in identifying particular sounds in a waveform display of sound data without listening to the sound data. Sound data received by a computing device is partitioned to form a plurality of sound data time intervals. A signature is computed for each of the plurality of sound data time intervals by the computing device based on features extracted from respective said sound data time intervals. The computed signatures are mapped by the computing device to one or more colors. Output of a waveform in a user interface is controlled by the computing device, in which the waveform represents the sound data and each of the sound data time intervals in the waveform have the mapped one or more colors.

Abstract: A method for recognizing an environmental sound in a client device in cooperation with a server is disclosed. The client device includes a client database having a plurality of sound models of environmental sounds and a plurality of labels, each of which identifies at least one sound model. The client device receives an input environmental sound and generates an input sound model based on the input environmental sound. At the client device, a similarity value is determined between the input sound model and each of the sound models to identify one or more sound models from the client database that are similar to the input sound model. A label is selected from labels associated with the identified sound models, and the selected label is associated with the input environmental sound based on a confidence level of the selected label.

Abstract: A pre-processing apparatus for speech recognition may include: a trailing silence period detection unit configured to detect the length of a trailing silence period contained in a speech signal; a reference trailing silence period storage unit configured to store the length of a reference trailing silence period; and a trailing silence period adjusting unit configured to adjust the length of the trailing silence period contained in the speech signal based on the length of the reference trailing silence period.

Abstract: Embodiments of apparatus and methods for voice based user enrollment with video assistance are described. In embodiments, an apparatus may include a face recognition module to identify a user from a first plurality of images and a lip motion detection module to detect the lip motion of the user from a second plurality of images. The apparatus may also include a recording module to activate a recording of the user. The apparatus may further include a user enrollment module, coupled with the recording module and the lip motion detection module, to establish a speaker model of the user based at least in part on the recording and the lip motion of the user. Other embodiments may be described and/or claimed.

Abstract: An enhanced find operation on a web page includes: activating an enhanced find operation on a web page and obtaining an entered keyword; obtaining one or more keywords on the web page related to the entered keyword and one or more categories associated with the one or more related keywords; displaying the one or more categories associated with the one or more related keywords with contents of the web page; detecting a selection of one of the one or more categories; and enhancing a display on the web page of the one or more related keywords associated with the selected category. Events for an activation of a find operation on the web page are monitored. In response to detecting the activation of the find operation, the find operation is intercepted, and the enhanced find operation is activated instead.

Abstract: A computer-implemented system and method for user-controlled processing of audio signals is provided. An audio signal including a reference segment and a segment preceding the reference segment is obtained. A value q is received from a user. Audio buffers in the preceding segment are defined, each having a width of N samples and a starting point a unique number of samples away from the preceding segment's start, based on a division of N by q. One or more of the buffers are transformed into discrete Fourier transform (DFT) buffers. A signature of the signal is generated using at least a portion of the reference segment and at least one of the DFT buffers. A new audio signal is received and a DFT for the audio signal is generated. The new audio signal is determined to match the audio signal based on a comparison of the DFT to the signature.

Abstract: A method of accessing a dial-up service is disclosed. An example method of providing access to a service includes receiving a first speech signal from a user to form a first utterance; recognizing the first utterance using speaker independent speaker recognition; requesting the user to enter a personal identification number; and when the personal identification number is valid, receiving a second speech signal to form a second utterance and providing access to the service.

Abstract: The system and method of separating speakers in an audio file including obtaining an audio file. The audio file is transcribed into at least one text file by a transcription server. Homogenous speech segments are identified within the at least one text file. The audio file is segmented into homogenous audio segments that correspond to the identified homogenous speech segments. The homogenous audio segments of the audio file are separated into a first speaker audio file and second speaker audio file the first speaker audio file and the second speaker audio file are transcribed to produce a diarized transcript.

Abstract: A speaker verification method is proposed that first builds a general model of user utterances using a set of general training speech data. The user also trains the system by providing a training utterance, such as a passphrase or other spoken utterance. Then in a test phase, the user provides a test utterance which includes some background noise as well as a test voice sample. The background noise is used to bring the condition of the training data closer to that of the test voice sample by modifying the training data and a reduced set of the general data, before creating adapted training and general models. Match scores are generated based on the comparison between the adapted models and the test voice sample, with a final match score calculated based on the difference between the match scores.

Abstract: A speaker intent analysis system and method for validating the truthfulness and intent of a plurality of participants' responses to questions. A computer stores, retrieves, and transmits a series of questions to be answered audibly by participants. The participants' answers are received by a data processor. The data processor analyzes and records the participants' speech parameters for determining the likelihood of dishonesty. In addition to analyzing participants' speech parameters for distinguishing stress or other abnormality, the processor may be equipped with voice recognition software to screen responses that while not dishonest, are indicative of possible malfeasance on the part of the participants. Once the responses are analyzed, the processor produces an output that is indicative of the participant's credibility. The output may be sent to proper parties and/or devices such as a web page, computer, e-mail, PDA, pager, database, report, etc. for appropriate action.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media relating to speaker verification. In one aspect, a system receives a first user identity from a second user, and, based on the identity, accesses voice characteristics. The system randomly generates a challenge sentence according to a rule and/or grammar, based on the voice characteristics, and prompts the second user to speak the challenge sentence. The system verifies that the second user is the first user if the spoken challenge sentence matches the voice characteristics. In an enrollment aspect, the system constructs an enrollment phrase that covers a minimum threshold of unique speech sounds based on speaker-distinctive phonemes, phoneme clusters, and prosody. Then user utters the enrollment phrase and extracts voice characteristics for the user from the uttered enrollment phrase.

Abstract: Animal feeders useful in feeding particular groups of animals are disclosed. Animal feeders described herein may, for example, include an electrically conductive exterior structure; a door; a door lock; a species recognition device; and an electric shock deterrent. Methods of feeding animals utilizing an electric shock deterrent are also disclosed.

Abstract: A user locked out of an account can gain access by allowing the user to reset the current password. An account access service can determine questions to ask the user. The account access service can maintain a trust level score, which is increased or decreased with each response to a question. Once this trust level reaches a certain predetermined amount, the user can regain access to the service, the account is unlocked, and the user can enter a new password to use.

Abstract: Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify a user of the communication device and/or the identity of a far-end speaker participating in a voice call with a user of the communication device. Knowledge of the identity of the user and/or far-end speaker is then used to improve the performance of one or more speech processing algorithms implemented on the communication device.

Abstract: In one embodiment, receiving, at a first computing device associated with a social-networking system and from a second computing device, a first request to verify an identity of a user of the social-networking system; sending, by the first computing device and to a mobile device associated with the user, a second request for information about the user; receiving, at the first computing device and from the mobile device, the information about the user; determining, by the first computing device, a confidence score indicating a probability that the identity of the user is true based on the information about the user received from the mobile device and information available to the social-networking system; and sending, by the first computing device and to the second computing device, the confidence score.

Abstract: One or more processing devices cause display of a graphical user interface (GUI) that includes a correlation search portion that enables a user to specify information for a key performance indicator (KPI) correlation search definition. The KPI correlation search definition includes search information and trigger determination information. The search information identifies KPI values, indicative of the KPI states, in a data store. The trigger determination information includes trigger criteria. The trigger determination evaluates the identified KPI values using the trigger criteria to determine whether to cause a defined action. A contribution threshold for a particular KPI definition is received via the GUI. The contribution threshold corresponds to a particular KPI state. The contribution threshold is stored as trigger criteria information.

Abstract: Techniques for authenticating users at devices that interact with the users via voice input. For instance, the described techniques may allow a voice-input device to safely verify the identity of a user by engaging in a back-and-forth conversation. The device or another device coupled thereto may then verify the accuracy of the responses from the user during the conversation, as well as compare an audio signature associated with the user's responses to a pre-stored audio signature associated with the user. By utilizing multiple checks, the described techniques are able to accurately and safely authenticate the user based solely on an audible conversation between the user and the voice-input device.

Abstract: A technique enables a user to participate in an online meeting. The technique involves receiving, by processing circuitry of a vehicle, a join instruction to join the online meeting. The technique further involves performing, by the processing circuitry of the vehicle, a communications exchange with a remote online meeting server in response to the join instruction, the communications exchange establishing an online meeting session with the remote online meeting server to join the processing circuitry of the vehicle to the online meeting. The technique further involves outputting, after the online meeting session is established and by the processing circuitry of the vehicle, video of the online meeting on a display screen which is integrated with the vehicle. Along these lines, the display screen can output a static image while the vehicle is moving and moving video while the vehicle is not moving (e.g., parked).

Abstract: A voice-responsive building management system is described herein. One system includes an interface, a dynamic grammar builder, and a speech processing engine. The interface is configured to receive a speech card of a user, wherein the speech card of the user includes speech training data of the user and domain vocabulary for applications of the building management system for which the user is authorized. The dynamic grammar builder is configured to generate grammar from a building information model of the building management system. The speech processing engine is configured to receive a voice command or voice query from the user, and execute the voice command or voice query using the speech training data of the user, the domain vocabulary, and the grammar generated from the building information model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a set of training utterances. The methods, systems, and apparatus include actions of obtaining a target multi-dimensional distribution of characteristics in an initial set of candidate utterances and selecting a subset of the initial set of candidate utterances based on speech recognition confidence scores associated with the candidate utterances. Additional actions include selecting a particular candidate utterance from the subset of the initial set of utterances and determining that adding the particular candidate utterance to a set of training utterances reduces a divergence of a multi-dimensional distribution of the characteristics in the set of training utterances from the target multi-dimensional distribution. Further actions include adding the particular candidate utterance to the set of training utterances.

Abstract: A device can be configured to receive speech input from a user. The speech input can include a command for accessing a restricted feature of the device. The speech input can be compared to a voiceprint (e.g., text-independent voiceprint) of the user's voice to authenticate the user to the device. Responsive to successful authentication of the user to the device, the user is allowed access to the restricted feature without the user having to perform additional authentication steps or speaking the command again. If the user is not successfully authenticated to the device, additional authentication steps can be request by the device (e.g., request a password).

Abstract: Computer-implemented systems and methods for extracting information during a human-to-human mono-lingual or multi-lingual dialog between two speakers are disclosed. Information from either the recognized speech (or the translation thereof) by the second speaker and/or the recognized speech by the first speaker (or the translation thereof) is extracted. The extracted information is then entered into an electronic form stored in a data store.

Abstract: In many scenarios, speaker verification systems can be given a single-channel audio with recordings of multiple speakers. To perform accurate speaker verification, a system can isolate the speech of a speaker. In one embodiment, a method, and corresponding system, of speaker verification includes extracting a target speaker's speech, using a known speaker voiceprint, from an audio recording that includes the target speaker's speech and the known speaker's speech. The known speaker voiceprint can correspond to the known speaker. Extracting the target speaker's speech can include determining portions of the audio recording where the known speaker voiceprint matches the known speaker's speech above a particular threshold, and extracting the target speaker's speech from other portions of the audio recording. In this manner, speaker verification is performed on the target speaker's speech without interference from the known speaker's speech and allows for a more accurate verification.

Abstract: The present invention utilizes speech analysis to provide real-time measurement of end-user stress, fatigue, and uncertainty in decision-making. The present invention monitors “technology-induced” stressors by increasing the inherent functionality of individual monitoring technologies, so as to perform multiple applications in a single setting. In addition to the continued use of speech recognition technology for computerized report transcription, the present invention simultaneously measures and analyzes occupational stress and fatigue in real-time, specific to the unique profile of each individual end-user and context of the task being performed. The derived user-specific stress/fatigue analytics may be used in the creation of a number of workflow and quality enhancing deliverables, including customizable intervention strategies for stress/fatigue reduction, creation of automated workflow templates, and targeted quality assurance and peer review.

Abstract: A system includes a processor configured to communicate, via a voice call, with a remote server over a connection established through a wireless phone in communication with the processor. The processor is also configured to deliver and receive data and instructions over a voice channel, using spoken, human-language-based communication. The processor is further configured to utilize a standardized voice, to dynamically form, transmit and interpret commands and data, including both predefined system commands and dynamically user-input variables relating to one or more system commands.

Abstract: A method, medium, and system generating a video abstract with high processing speeds, may include a detecting of an event candidate section from video data, based on audio information, a detecting of shot change information from the detected event candidate section, a detecting of final event sections from the detected event candidate section, based on the detected shot change information and visual information, and a generating of video abstract information by merging the extracted final event sections.

Abstract: A system and method for parallel speech recognition processing of multiple audio signals produced by multiple microphones in a handheld portable electronic device. In one embodiment, a primary processor transitions to a power-saving mode while an auxiliary processor remains active. The auxiliary processor then monitors the speech of a user of the device to detect a wake-up command by speech recognition processing the audio signals in parallel. When the auxiliary processor detects the command it then signals the primary processor to transition to active mode. The auxiliary processor may also identify to the primary processor which microphone resulted in the command being recognized with the highest confidence. Other embodiments are also described.

Abstract: An approach is provided for providing biometric information processing using distributed computation. A biometric information processing infrastructure determines to receive an input including, at least in part, biometric information. The biometric information processing infrastructure selects one or more analyses for processing the input. The biometric information processing infrastructure also determines one or more processes associated with the one or more analyses. The biometric information processing infrastructure further determines to derive one or more computation closures from the one or more processes. The biometric information processing infrastructure determines to decompose the one or more computation closures for distribution in one or more computation spaces.

Abstract: Methods, systems, computer-readable media, and apparatuses for utilizing voice biometrics to prevent unauthorized access are presented. In some embodiments, a computing device may receive a voice sample. Subsequently, the computing device may determine a voice biometric confidence score based on the voice sample. The computing device then may evaluate the voice biometric confidence score in combination with one or more other factors to identify an attempt to access an account without authorization.

Abstract: In one embodiment, a computer system stores speech data for a plurality of speakers, where the speech data includes a plurality of feature vectors and, for each feature vector, an associated sub-phonetic class. The computer system then builds, based on the speech data, an artificial neural network (ANN) for modeling speech of a target speaker in the plurality of speakers, where the ANN is configured to discriminate between instances of sub-phonetic classes uttered by the target speaker and instances of sub-phonetic classes uttered by other speakers in the plurality of speakers.

Abstract: Methods, systems, and computer program products are provided for asynchronous communications. Embodiments include receiving a recorded message, the message recorded on a handheld device; converting the recorded message to text; identifying a recipient of the message in dependence upon the text; associating the message with content under management by a library management system in dependence upon the text; and storing the message for transmission to another handheld device for the recipient. Embodiments also typically include recording a message on handheld device and transferring a media file containing the recorded message to a library management system. Embodiments also typically include transmitting message to another handheld device.

Abstract: According to an embodiment, an information processing apparatus includes a dividing unit, an assigning unit, and a generating unit. The dividing unit is configured to divide speech data into pieces of utterance data. The assigning unit is configured to assign speaker identification information to each piece of utterance data based on an acoustic feature of the each piece of utterance data. The generating unit is configured to generate a candidate list that indicates candidate speaker names so as to enable a user to determine a speaker name to be given to the piece of utterance data identified by instruction information, based on operation history information in which at least pieces of utterance identification information, pieces of the speaker identification information, and speaker names given by the user to the respective pieces of utterance data are associated with one another.