345results about "Audio data querying" patented technology

The invention discloses a conference record generation method based on voice recognition, and further discloses an electronic device and a computer storage medium. The conference record generation method comprises the steps that a conference record generation instruction sent by a user is received, and audio to be converted is acquired; sentence division is performed on the to-be-converted audio,and audio sentences of the to-be-converted audio are obtained; voiceprint features are extracted from the recognized audio sentences separately, the voiceprint features corresponding to the audio sentences are compared with a preset voiceprint feature library for analysis to determine speaker identity information corresponding to each audio sentence, and the audio sentences are divided into voicesegments according to the speaker identity information to determine a voice segment set corresponding to the to-be-converted audio; target voice recognition models corresponding to the voice segmentsare called to sequentially obtain text corresponding to each voice segment; and a conference record corresponding to the to-be-converted audio is generated. By using the conference record generation method based on voice recognition, accuracy and efficiency of conference record generation can be improved.

Media suitable for a designated style of use are recommended from among a database of media objects. A prediction engine is trained using a plurality of media object lists, each of the media object lists containing metadata associated with a plurality of media objects, the media object lists corresponding to the designated style of use, and the prediction engine being trained to calculate the likelihood that a media object is suitable for the designated style of use. The prediction engine includes a binomial classification model trained with feature vectors that include behavioral data, acoustic data and cultural data for the plurality of media objects. The trained prediction engine is applied to media objects in the database of media objects so as to calculate likelihoods that the media objects are suitable for the designated style of use. One or more media objects are recommended using the calculated likelihoods.

An voice command processing method provides a unified voice control interface to access and control Internet of things (IoT) devices and configure value of attributes of graphical user interface (GUI) elements, attributes of applications, and attributes of the IoT devices. As a voice command comprises an expression of a percentage or a fraction of a baseline value of an attribute, or an exact value of the attribute of an IoT device, the unified voice control interface sets the attribute of the IoT device in response to the percentage, the fraction, or the exact value in the voice command.

A method and apparatus are provided for a first controlled device, such as a wireless local transmitter that accepts a plurality of digital audio signals and corresponding program information signals converted from a controlled source, such as the encoded digital data provided by a digital data signal source, typically a community antenna television (CATV) cable or direct broadcast satellite, then modulates said digital audio and corresponding program information signals on different carrier frequencies and transmits the modulated signals to a plurality of second controlled devices, such as remote digital receiver / tuners that demodulate said signals to output music in stereophonic sound and display the corresponding program information by means of an alphanumeric display. The first and second controlled devices contain microprocessor systems for communicating, controlling, storing, processing, and display of digital data within the operation of the respective system. A high speed, error free digital signal protocol is utilized for transmitting digital audio and corresponding program information signals to and from the digital receiver / tuner. The digital data transmitter and digital receiver / tuners utilize the 44.1 kilohertz (kHz) Compact Disc (CD) clock signal embedded in digital audio signals provided by an established delivery system to derive clocking signals for reception and processing of digital audio signals and for implementing the display information communications protocol.

System for providing music to users.

The invention discloses a rhythm point recognition method and device, an electronic device and a storage medium. The method comprises the following steps of determining at least one alternative rhythmpoint in an audio signal according to the spectral characteristics of the audio signal to be identified, and obtaining the starting point time corresponding to each alternative rhythm point; mappingeach alternative rhythm point into a trend fitting envelope signal of the audio signal according to the corresponding starting point time, and determining a target rhythm point in each alternative rhythm point according to the waveform characteristics of the trend fitting envelope signal; and determining volume information corresponding to each target rhythm point according to the beat informationof the audio signal, fitting an envelope signal and the beat information of the audio signal according to the fluctuation of the audio signal, and determining the duration corresponding to each target rhythm point. According to the embodiment of the invention, the rhythm points can be automatically and accurately identified, and the rhythm point identification efficiency is improved.

The invention discloses an article recommendation method based on Chinese similarity calculation. The method comprises the following specific steps of crawling the main content of an article by utilizing a Python crawler program; obtaining a word vector according to the main content of the crawled article, and training; converting the article to be recommended into a word vector matrix; and converting the keyword word group of the user into a matrix, reading the word vector matrix converted from the article obtained in the previous step, carrying out standardized processing on the word vectormatrix data, carrying out the matrix calculation, and carrying out arrangement according to a similarity coefficient. The invention provides the article recommendation method based on Chinese similarity calculation, which can help an internet user to efficiently mine the interested articles, and is larger in application range, lower in manual marking cost and good in recommendation diversity.

An excerpt of a media object is extracted by computing, for each bar of an N-bar loop, one or more perceptual quality vectors. For each of the one or more perceptual quality vectors within a search zone (S), one or more distances between bar i and bar i+N is computed and sorted to generate a sorted list of bars.

The invention discloses a ground-to-air call data analysis method and a ground-to-air call data analysis system based on voice recognition. The method comprises the steps of continuously collecting and storing ground-to-air call voice data and radar data by means of an air traffic control recorder; converting into a wav format file through adaptive decoding; intercepting a complete statement to form a voice file through an endpoint detection technology based on deep learning; converting the voice file into text information through an air traffic control voice recognition model based on deep learning; determining control instruction intention and parameters through an air traffic control semantic understanding model based on deep learning; and performing ground-air call data analysis such as voice and instruction data statistical analysis, monitoring data and voice synchronous playback, key monitoring and the like based on each generated file. According to the method provided by the invention, the efficiency and accuracy of ground-air call data analysis work are comprehensively improved. The problem that during the air traffic control safety management practice, the control commandquality evaluation and the after-event analysis are carried out by completely relying on manual listening, recording, query and statistical analysis of ground-air calls is solved.

The present invention discloses a sharing method and device of network works, a server and a storage medium. The method comprises the following steps of: selecting original works shared on a network page; employing new works uploaded by a user, and performing derivative work on the original works to obtain shared works; and performing sharing of the shared works on the network page. In the invention, the sharing method and device of network works, the server and the storage medium form shared works through joint derivative work of the original works and the new works to enrich the resources ofthe shared works, reduce the creation difficulty of the shared works and allow more users to take part in the creation of the shared works.

An information processing method of an information processing system including a client device functioning as a client and a server device functioning as a server which are capable of communication via a network, includes the steps of: at the server device, managing format identification information provided so as to be unique for each content data within the range of each data format, corresponding to the contents of each content; at the client device, causing execution of communication via network, for specifying a content, as to the server device; at the server device, transmitting, to the client device, format identification information correlated with a specified content in response to specification of a content via network from the client device; and at the client device, managing the received and obtained format identification information as corresponding to the specified content.

Disclosed are systems and methods for wirelessly recording multi-track audio files without the data corruption or loss of data that typically occurs with wireless data transmission. In some aspects of the present invention, each performer is equipped with a local audio device capable of locally recording the respective performer's audio while also transmitting it to a master recorder. The locally recorded audio may then be used to repair or replace any audio lost or corrupted during transmission to the master recorder. Such repair or replacement may be performed electronically or via playback of the locally recorded audio. In other aspects of the present invention, a master recorder is not required since all locally recorded audio may be combined or otherwise processed post-recording. Locally recorded audio may include identifiers to aid in post-recording identification of such audio. A multi-memory unit is also provided to facilitate manipulation and processing of audio files.