Abstract: An immersive display system is provided. The immersive display system obtains an image and determines external media elements based on the image. The immersive display system renders the external media elements along with the image to provide and immersive display experience to a user.

Abstract: A first zone player engages in synchronous playback of given audio content by obtaining the given audio content, generating and placing representative audio frames into a buffer, and transmitting the audio frames to a second zone player to play the given audio content in synchrony with the second zone player. After receiving a command to pause the synchronous playback, the first zone player prepares for a fast-resume by identifying a location in the given audio content and retaining some of the audio frames in the buffer for use during the fast-resume. The first zone player then initiates the fast-resume by determining a future resume time, transmitting an instruction to the second zone player to resume playback at the future resume time, and at the future resume time, resuming use of the audio frames in the buffer, starting at the identified location, to play the given audio content in synchrony.

Abstract: Disclosed is a method for determining an authenticity of at least a portion of an audio stream of a voice call connection. In the method it is received a request for confirming an authenticity of at least portion of an audio stream of a voice call connection; detected a number of voice call connection specific watermark patterns included in the portion of the audio stream in question; and set, in accordance with a detection of the number of the voice call connection specific watermark patterns included in the portion of the audio stream, a detection result to express one of the following: i) the portion of the audio stream is authentic, ii) the portion of the audio stream is nonauthentic. Also disclosed is a network node, a computer program product and a system.

Abstract: Audio based transactions are getting more popular and are envisaged to become common in years to come. With the rise in data protection regulations, muting portions of the audio files is necessary to hide sensitive information from an eavesdropper or accidental hearing by an entity who gets unauthorized access to these audio files. However, it is realized that deleted transaction information in a muted audio files make audit of the transaction challenging and impossible. Embodiments of the present disclosure provide systems and methods of muting audio information in multimedia files and retrieval thereof which is masked and further allows for reconstruction of the original audio conversation or restoration Private to an Entity (P2aE) information without original audio reconstruction when auditing is being exercised.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a memory configured to store a voice recognition application, and a processor configured to execute the voice recognition application based on receiving a voice input initiation signal. The processor is configured to control a communication interface comprising communication circuitry to establish a session with a voice recognition server before the voice recognition application is executed.

Abstract: A correlation function having a clear peak is generated even in an environment in which an ambient noise level is high. A correlation function generation apparatus (100) includes a plurality of input signal obtaining units (101), a changing unit (102), a cross-spectrum calculator (103), a variance calculator (104), and a correlation function calculator (105). The input signal obtaining unit (101) obtains a wave generated by a wave source as an input signal. The transformer (102) obtains a plurality of frequency domain signals by transforming a plurality of input signals obtained by the plurality of input signal obtaining units. The cross-spectrum calculator (103) calculates a cross-spectrum based on the plurality of frequency domain signals. The variance calculator (104) calculates the variance of the cross-spectrum. The correlation function calculator (105) calculates and generates a correlation function based on the cross-spectrum and the variance.

Abstract: An example implementation involves a playback device receiving a request to add continuous automated streaming audio content to a playback queue, the request indicating a playback start time, and the playback queue indicating a plurality of audio content. The implementation further involves the playback device adding the continuous automated streaming audio content to the playback queue. The example implementation also involves the playback device determining that a duration until the playback start time is less than a duration of the given audio content before playing a given audio content in the playback queue. The example implementation involves the playback device responsively, playing the continuous automated streaming audio content.

Abstract: The present disclosure relates to a method and apparatus for processing a multimedia signal. More specifically, the present disclosure relates to a method comprising obtaining at least one video object from the multimedia signal and at least one audio object from the multimedia signal, extracting video feature information for the at least one video object and audio feature information for the at least one audio object, and determining a correlation between the at least one video object and the at least one audio object through an object matching engine based on the video feature information and the audio feature information, and an apparatus therefor.

Abstract: A method, system, and computer program product for using a natural language processor to find nodes in a span include providing a parse tree including a trigger node, a first target node connected to the trigger node by a first edge, and a second target node connected to the first target node by a second edge, wherein first trigger node includes a first attribute and a second attribute, and wherein the target node includes a third attribute and a fourth attribute. Further included are recording the first, second, third, and fourth attributes in a first tree table; creating a first consideration table from the first tree table, the first consideration table including the first, second, third, and fourth attributes; and evaluating the first target node to determine whether the first node belongs in a first span that includes the first trigger node.

Abstract: A verification device is configurable for verifying the identity of a person. The verification device may be in communication with a user device and an entity device that may request an authorization decision from the verification device. The verification device may have a collection system configured to populate a voice profile database with a plurality of voice profiles in the form of audio recordings of people. The verification device may also have a testing system configured to select one of the voice profiles, provide the voice profile to an end-user device, and receive an answer from the end-user device, the answer being an attempt by the person to identify an individual associated with the voice profile. The verification device may further have an authentication system configured to determine whether the identity of the person is verified based on the answer from the end-user device.

Abstract: A host device is connected via universal serial bus (USB) connections to one or more external devices with respective speakers. The host device synchronizes playback of audio through the speakers of the USB-connected external devices by requiring devices to implement a deterministic latency between receipt of a start playback request, and requiring devices to slave their audio clocks to USB start-of-frame tokens, and determining a buffered start time for starting data transmission to the respective USB devices. The buffered time equates to the current time of the USB host plus an additional time buffer. The host device waits until the buffered start time, and then starts transmitting the audio stream to the external devices, which, in turn, begin playing the audio data on the next available clock cycle, frame, or microframe.

Abstract: Various embodiments for managing dialog comments by a processor are provided. Each communication of a dialog communicated by one or more users using one of a plurality of applications may be monitored, tracked, and/or analyzed using a machine learning operation and/or a natural language processing operation. A topic trajectory of the dialog may be identified between one or more users using one of a plurality of applications. A selected comment submitted by the one or more users may be automatically transformed according to one or more corrective actions upon the selected communication deviating from the topic trajectory.

Abstract: Techniques for cognitive analysis of documents are provided. A document corresponding to a clinical trial is received. Criteria are identified for the clinical trial based on processing the electronic document using natural language processing (NLP) techniques, where the criteria specify attributes of individuals that are eligible for the trial. Further, the criteria are analyzed using NLP techniques to determine a respective confidence level for each respective criterion, where the confidence level indicates a degree of certainty that the criterion is applicable to the trial. A knowledge graph is generated based at least in part on the clinical trial, where the confidence level assigned to each criterion is included in the knowledge graph for subsequent use. Finally, one or more therapies in the knowledge graph are selected to be recommended, based on a patient profile and the confidence level assigned to each of the criteria.

Abstract: Language models may be run with an input set of words in a given sentence. Each of the language models can predict a set of next candidate words to follow the input set or words. Based on the sets of next candidate words predicted by the language models and an actual next word, language guidance can be provided.

Abstract: The present invention relates to systems for communicating data. In particular, systems for communicating data to and from mobile devices are described. One system involves the use of a server to store the association between a shortcode and the data. A user device can be used to transmit the shortcode to a second user device. The second user device can then access the association at the server to access the data. The shortcode is transmitted via an audibly unique signal between the two devices. Further devices, systems, and methods for redeeming vouchers, transferring money, unlocking content on a device, and authenticating transactions all using audio are also disclosed. A method for managing data communication on a mobile device is further disclosed. In addition, a system for asynchronous transmission of the data is disclosed by use of reserving a shortcode at a server before the shortcode is associated with data.

Abstract: In some examples, artificial intelligence based music playlist reordering and song performance assessment may include ascertaining listening data for a plurality of tracks, and generating a plurality of sessions. Tracks that have been played more than a specified play threshold may be identified and retained. Sessions that are greater than a minimum session length threshold and less than a maximum session length threshold may be retained. Input-output track sequences may be generated for the retained sessions. Unique identifiers may be assigned to each of the tracks present across the retained sessions. Each input-output track sequence may be vectorized based on associated unique identifiers. A neural network model may be trained based on the vectorized input-output track sequences. For an input playlist, the trained neural network model may be used to generate a modified playlist. Additionally or alternatively, a user-song interaction graph may be used to generate another modified playlist.

Abstract: An example method may include recording, via a microphone of a first playback device, audio played by a second playback device in accordance with a calibration setting. The method may further include, based on the recorded audio, determining that the calibration setting is invalid. The method may further include, in response to determining that the calibration setting is invalid, sending an indication that the calibration setting is invalid. This disclosure also includes example non-transitory computer readable media and playback devices that are related to the example method.

Abstract: Systems and methods are disclosed herein for selective audio segment compression for accelerated playback of media assets by service providers. A playback speed of the video segment of a media asset is calculated based on the duration of the video segment and a received playback time period. The system receives audio segments and corresponding priority weights. The audio segments with the lowest priority weight are removed from the group of various audio segments. The system then determines whether the duration of the remaining audio segments exceeds the received playback time period. If so, the system modifies the remaining audio segments by removing another audio segment with the lowest priority weight from the remaining audio segments. The system then rechecks whether the received playback time period is exceeded. If not, the system generates for playback the video segment based on the video playback speed and the remaining audio segments.

Abstract: An input item information DB stores input items and weighting factors for each service based on voice recognition, a specifying unit specifies the input items based on uttered information, a storage unit stores the uttered information for the specified input items, a calculation unit calculates a score for each service based on all the input items for which the uttered information is stored and the weighting factors, and a request unit requests a user to utter information for an uninput item for which the uttered information has yet to be stored in the service having the highest score. The request unit requests the user to utter the information for the uninput item for a service having the least number of uninput items in the indispensable input items or having the highest ratio of input for the indispensable input items among the services having the highest score.

Abstract: A processor-implemented machine translation method includes translating a source sentence expressed in a source language into a target language to determine a target sentence, determining, based on a reliability of the target sentence, whether the target sentence is appropriate as a translation result of the source sentence, and re-determining a target sentence corresponding to the source sentence in response to a result of the determining being that the target sentence is inappropriate as the translation result.