93results about "Audio data retrieval" patented technology

A method and a system for managing sharing of a video in a collaboration session are disclosed. A sharing function obtains (B122) a synchronization time stamp of an audio frame of the collaboration session, wherein the audio frame is going to be used for synchronizing the shared video stream with the collaboration session. The sharing function determines, based on a video frame rate difference between the desired frame rate and a source frame rate of the video file, whether more, less or same number of video frames as in the video file are needed in the shared video stream. The sharing function iteratively retrieves (B140) video frames from the video file stored in the storage function (140). The sharing function provides (B160), by the sharing function (112), the shared video stream by sending said one or more generated video frames to the video communication service (110). The video communication service provides (B174), the shared video stream to the two client devices participating in the collaboration session.

Systems, methods, and apparatuses for implementing a behavioral health engagement platform are described herein. For example, according to one embodiment there is a method performed by a behavioral health engagement platform (“platform”) having at least a processor and memory therein, in which the method includes: receiving a request at the platform from a therapist user device requesting access to the platform; generating, at the platform, a therapist GUI interface based upon the request; receiving therapist user input at the platform via the therapist GUI interface specifying a diagnostic modality for a patient, wherein content is selected by the platform based on the therapist-defined diagnostic modality; transmitting the content to a patient GUI interface for display at a patient user device; receiving patient user input at the platform from the GUI interface displayed to the patient user device, wherein the patient user input specifies one or more of: (i) selection of an avatar, (ii) responses to questions about the patient's compliance with treatment, (iii) responses to questions about the patient's emotional state and triggers before and after (iii) the viewing and rating of the platform-selected content, and (iv) biometric feedback from the patient; modifying the platform-selected content and sequence to be transmitted to the patient user device based upon the patient user input; sending the platform-selected content to the patient GUI interface at the patient user device in accordance with the sequence and modifications determined by the platform; creating alert notifications at the platform; sending the alert notification to the therapist GUI interface; and monitoring and promoting positive behavioral health outcomes. Other related embodiments are disclosed.

A playback device comprising a first spectrum radio for communication via a first wireless spectrum and a second spectrum radio for communication via a second wireless spectrum operates in a first mode in which the first spectrum radio is enabled and the second spectrum radio is disabled. While operating in the first mode, the playback device receives a command to join a synchrony group with a display device. Based on the command, the playback device begins to operate in a second mode in which the second spectrum radio is enabled. The playback device receives audio content for playback, wherein the audio content corresponds to video content being displayed at a display device. Using the second spectrum radio, the playback device coordinates with the display device for playing back the audio content in synchrony with the video content.

An audio processing system is disclosed for comparing a query audio sample with a database of multiple reference audio samples using an external normalization. The system includes at least one processor and memory storing instructions that, when executed by the processor, cause the system to determine a bias term of the external normalization based on a spectro temporal pattern of the query audio sample. The system further compares the query audio sample with each of the reference audio samples to generate a similarity score for each comparison. The system combines the bias term with each of the similarity scores to produce normalized similarity scores. The normalized similarity scores are then compared with a threshold to generate a result of comparison, which is subsequently outputted.

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.

A computer-implemented method, performed by a system, for creating a video representation of a file is disclosed. The method comprises receiving, by the client device a request to start a synchronization addon with a file, whose content is requested to be shared by a user of the client device, wherein synchronization of data, collaborated on in the collaboration session, is performed by a synchronization framework used by the synchronization addon, and receiving, by the recording function, a message, originating from the client device instructing the central server to capture image frames of the content displayed by an instance of the synchronization addon. The method further comprises listening, by the recording function, to event messages from the synchronization addon executing in the recording function, and determining, by the recording function, a respective event time stamp for each respective event message of the event messages to obtain metadata associated with the content.

Methods, systems, and devices for abnormal sound detection are described. An audio recording of a mechanized environment may be obtained. First sounds extracted from the audio recording may be categorized into a set of categorical sounds. A library of first sound patterns may be generated using the categorical sound and based on second sounds extracted from the audio recording. The first sound patterns may include sequences of the categorical sounds. Audio data including audio signals capture by sensors in the mechanized environment may be received, and second sound patterns detected in the audio signals may be compared with the first sound patterns. Based on comparing the second sound patterns with the first sounds patterns, a sound pattern that is not in the library of the first sound patterns may be identified. An alarm may be generated based on detecting the sound pattern a threshold quantity of times.

The present application relates to apparatus and methods for cellular composition. Embodiments of the invention provide systems, methods and apparatus for real-time cellular composition / generation of music using cells (i.e. short musical motifs), wherein the cellular composition relies on user data.

To converse with an avatar more naturally.SOLUTION: An information processing method is executed by an information processing device, and includes: a storing step for vectorizing a document of a conversation and associatively storing the document of the conversation and the vector of the document; an acquiring step for acquiring a voice of a user; a converting step for performing text conversion and vector conversion on the acquired voice; an extracting step for extracting a vector of the document corresponding to the vector obtained by the conversion; a generating step for generating an answer to the voice acquired based upon the document of the conversation corresponding to the extracted vector of the document; and an uttering step for uttering the generated answer.SELECTED DRAWING: Figure 6

A content provision system in which a script that is generated by a creator and includes identification information of content and comment information is stored in a predetermined storage medium to be browsable by a user, the content providing system including a control unit that performs control to execute reading, according to a script selected by the user, content indicated by content identification information included in the script by using a right that the user has already acquired by a contract with a specific service, and provide the content to the user, and control to read a comment according to the comment information included in the script and provide the comment to the user at least one of before or after the provision of the content.

Methods, systems, and computer program products are presented herein for rendering synchronous audio using audio rendering devices. A networked audio rendering device may include a first wireless communications module, a second wireless communications module, a microcontroller, at least one speaker driver, and at least one digital audio amplifier. Audio data may be received by a first wireless communications module. Timecode data may be received by a second wireless communications module operating at a sub-GHz ISM band. The audio data may be received by a microcontroller. The audio data is processed by the microcontroller to generate output audio signals based on the timecode data. The output audio signals may be amplified by at least one digital audio amplifier. At least one speaker driver may be driven, by the at least one digital audio amplifier, to render an audio output.

The application provides a voiceprint registration method, device, equipment and storage medium, the method comprises the following steps: storing the audio to be registered according to the time length of the audio to be registered when obtaining one audio to be registered every time; acquiring the first type of audio from the stored several audios based on a plurality of small file consumption service threads, and performing voiceprint registration on the first type of audio based on the operation equipment; and acquiring the second type of audio from the stored several audios based on a single large file consumption service thread, and performing voiceprint registration on the second type of audio based on the operation equipment; wherein the audio time length of the second type of audio is greater than the audio time length of the first type of audio. The voiceprint registration method provided by the application can perform voiceprint registration on short audios in a multi-thread concurrent manner (concentrate processing short audios), and perform voiceprint registration on long audios in a single thread, so that the resource utilization rate of the operation equipment can be effectively improved, the efficiency of voiceprint registration can be effectively improved, and the hardware cost can be greatly saved.

A computer-implemented method for managing a file is disclosed. The method comprises opening (E110) the file by means of a rendering function (610) to render at least a portion of the file as an image, and obtaining (E120) one or more event messages. For each event message of said one or more event messages, the method comprises obtaining (E130), from the rendering function (610), an image for each event message, wherein the image represents a rendered portion of the file, wherein the image is associated with a sequence indication, generating (E140) metadata based on the event message and the sequence indication, providing (E150) the metadata, and providing (E160) a video comprising a set of images, wherein the set of images comprises the image for said each event message, wherein the video is a representation of the file.

A first user equipment (UE) may obtain a command from a driver of a vehicle that includes an indication of a driver-specified direction (DSD). The first UE may adjust a priority of objects detected within a sensor area of a set of sensors based on the indication of the DSD. To adjust the direction of the set of sensors, the first UE may transmit a signal to a second UE that includes at least one of the indication of the DSD or a second indication of the sensor area. The first UE may transmit the signal using a V2X communication link with the second UE. The first UE may receive a set of sensor results associated with the sensor area from the second UE. The first UE may output a sensor report based on the received set of sensor results.

An audio processing system is disclosed for comparing a query audio sample with a database of multiple reference audio samples using an external normalization. The system includes at least one processor and memory storing instructions that, when executed by the processor, cause the system to determine a bias term of the external normalization based on a spectro-temporal pattern of the query audio sample. The system further compares the query audio sample with each of the reference audio samples to generate a similarity score for each comparison. The system combines the bias term with each of the similarity scores to produce normalized similarity scores. The normalized similarity scores are then compared with a threshold to generate a result of comparison, which is subsequently outputted.

A computer-implemented method for managing files is disclosed. The method comprises: opening (E110) the file by a rendering function (610) to render at least a portion of the file as an image; and obtaining (E120) one or more messages. For each event message of the one or more event messages, the method comprises: acquiring (E130) an image for each event message from the rendering function (610), where the image represents a rendered portion of the file, where the image is associated with a sequence indication; generating (E140) metadata based on the event message and the sequence indication; providing (E150) the metadata; and providing (E160) a video comprising a set of images, where the set of images comprises the image for each event message, where the video is a representation of the file.

The management of virtual content permissions for digital assets in a virtual environment includes: receiving data indicating a request from a user to assign virtual content permissions to digital assets; determining whether the requested virtual content permissions are available for assignment to the user and a set of terms for the assignment of the requested virtual content permissions; notifying the user of availability and a set of terms for assigning virtual content permissions to the user; receiving data indicating that the user agrees to the assignment, the data including at least one term from the set of consent terms; and updating the virtual content permissions database to indicate the assignment of virtual content permissions to the user.

Disclosed is a system provides substantially synchronized streaming. The system comprises at least one server operable to communicate, over a network, with client devices connected to the Internet; and provide a media stream to the client devices such that the media stream is displayed, in a substantially synchronized manner, on display screens of the client devices.

Disclosed is a media sharing system that provides shared experiencing of licensed media content such as movies. The system includes a web server that communicates with multiple client devices over the internet whereby a user's multiple social contacts can participate in a synchronized stream of licensed media content such as movies. The system is able to schedule the multi-user experiencing of the licensed media content and further synchronize the streaming of the licensed content so the participating users receiving the media streams in a substantially synchronized manner. The system still further provides for social content interaction amongst the multiple recipients so that the multiple users can interact in a time-contextual manner consistent with the substantially synchronized receipt of the licensed media content.

A first user equipment (UE) may obtain a command comprising an indication of a driver-specified direction (DSD) from a driver of a vehicle. The first UE may adjust a priority of objects detected within a sensor area of a set of sensors based on the indication of the DSD. To adjust the direction of the set of sensor, the first UE may transmit, to a second UE, a signal including at least one of the indication of the DSD or a second indication of the sensor area. The first UE may transmit the signal using a V2X communication link with the second UE. The first UE may receive, from the second UE, a set of sensor results associated with the sensor area. The first UE may output a sensor report based on the received set of sensor results.

Embodiments are provided for causing a playback device to pre-cache audio content in a playback queue. An example implementation involves a playback device detecting by a sensor on the playback device, movement in relation to the playback device. In response to detecting the movement, the playback device identifies a particular media item in a playback queue associated with the playback device. Prior to receiving a user command to play the media item, the playback device stores at least a portion of the particular media item in memory on the playback device.

The invention provides a method and a system for generating a high-quality voice database. The method comprises the following steps: collecting a set number of seed voice data; generating target text data by using the seed sound data, and preparing a text needing to be synthesized; by adopting a sound cloning technology based on an AI large model, a deep learning algorithm and a large amount of data training are utilized to realize high-precision imitation and replication of the sound of a specific speaker, and voice data are generated; and performing audio data quality verification on the generated voice data, removing unqualified voice data, ensuring the quality of the voice database, and obtaining a high-quality voice database. According to the invention, the cost of voice data acquisition is greatly reduced, a large amount of high-quality voice data can be quickly generated, the manufacturing period of a voice database is remarkably shortened, and the efficiency of voice data acquisition is improved; the consistency of the generated voice data and the corresponding text is improved, the accuracy and naturalness of the voice data are ensured, and the overall quality of the voice database is improved.

Including an asynchronous media fabric service in each of a plurality of hosts. The hosts operating together to asynchronously process real-time media streams under control of a media-processing application. A media-processing function process operates to capture from a real-time synchronous input stream and / or output to a real-time synchronous output stream. A grain transfer link is established for a transfer of grains between a first instance of a first shared memory pool located on a first host and a second instance of the first shared memory pool located on a second host. Following a first local write operation of a first grain to the first instance of the first shared memory pool, the asynchronous media fabric service is notified by a producer function process that the first grain is available for transfer to the second instance of the first shared memory pool on the second host via the grain transfer link.

A system and method for an asynchronous media fabric service. The system includes at least one host configured with the asynchronous media fabric service. The asynchronous media fabric service is configured to: create and delete shared memory pools that are used to allow processes running on a single host direct access to grain data; send and receive grains from other hosts; and serve as an API endpoint for asynchronous media fabric function processes to create, delete and obtain references to streams.

A system is configured to (1) receive data indicating a first command to present media content at a display device of a media playback system that comprises a playback device, (2) determine a playback condition comprising a user identity, (3) identify, from one or more user accounts associated with the playback device, a given user account corresponding to the user identity, (4) based at least on (i) the first command and (ii) at least one property of the given user account, identify a set of media items that are to be presented, (5) cause the set of media items to be presented at the display device, (6) receive data indicating a second command to play back at least one given media item from the set of media items presented at the display device, and (7) cause the playback device to play back the at least one given media item.

A threat detection system includes a memory storing training datasets including threat-positive audio data, threat-negative audio data, and background noise audio data; and instructions to implement a first machine learning model and a second machine learning model. The system includes a processor coupled to the memory and configured to train the first machine learning model to detect an existence of a threat in arbitrary audio data using the threat-positive audio data and the threat-negative audio data; overlay the background noise audio data with the threat-positive audio data to generate overlayed threat-positive audio data; overlay the background noise audio data with the threat-negative audio data to generate overlayed threat-negative audio data; and train the second machine learning model to detect the existence of the threat in arbitrary audio data using the overlayed threat-positive audio data and the overlayed threat-negative audio data.

Methods and systems for sourcing supplemental content are disclosed. Secondary devices may be used to identify content streaming on first screen devices and to generate supplemental data for the content. In this manner, users may be leveraged to create various data for a variety of content. The data may be collected and organized so that users watching content at a later time may have access to the data. Methods and systems for using second screen devices to access metadata created by the crowd are also disclosed.

To easier provide a content and a comment on it.SOLUTION: The present invention provides a content provision system comprising a control part in which a script formed by at least text information in regard to identification information of a content and an advertisement is stored in a predetermined storage medium so as to enable a browsing by a user; in accordance with the script selected by the user, a reading of a content indicated by content identification information contained in their script is controlled so that the content is executed and provided to the user by utilizing the rights that the user has already acquired via a contract with a specific service; and the text information contained in the script is formed by a voice synthesis, and is provided to the user at least either before or after a provision of the content.SELECTED DRAWING: Figure 1

Provided is an information processing device comprising: a data acquisition unit that acquires music track data and music track-related data associated with the music track data; a feature value calculation unit that calculates a feature vector of a first dimension from the music track data; and a dimensionality reduction unit that converts the feature vector of the first dimension into a feature vector of a second dimension capable of visualizing the feature vector of the first dimension by using a trained model obtained by training the relationship between the feature vector of the first dimension and the music track-related data.