Abstract:
A method performed by a surgical system. The method includes receiving 1) a video stream captured by a camera inside an operating room and 2) an audio stream that includes sounds captured by a microphone inside the operating room. The method detects an audio event within the operating room by performing an acoustic analysis upon the audio stream. The method produces a timestamp based on the detected audio event and based on an internal clock of the electronic device and tags the timestamp to the video stream and the audio stream. The method stores the tagged image stream and the tagged audio stream in memory.
Abstract:
A method and an apparatus of processing audio data, an electronic device, a storage medium, and a program product are provided, which relates to a field of artificial intelligence, in particular to a field of speech processing technology. The method includes: processing spectral data of the audio data to obtain a first feature information; obtaining a fundamental frequency indication information according to the first feature information, wherein the fundamental frequency indication information indicates valid audio data of the first feature information and invalid audio data of the first feature information; obtaining a fundamental frequency information and a spectral energy information according to the first feature information and the fundamental frequency indication information; and obtaining a harmonic structure information of the audio data according to the fundamental frequency information and the spectral energy information.
Abstract:
A method and system for providing a user with feedback on performance of a karaoke song is provided. Musical data elements (e.g. lyrics and notes) of a music track input feed are compared with musical data elements (e.g. lyrics and pitch) of the karaoke performance. Based on the comparison, a feedback on the performance is generated on a display in substantially real time. Accordingly, text of the lyric of the music track and text of the the lyric of the performance are represented on the display. Moreover, differences between the performance and the music track are represented by altering the representation of the lyrics of the performance relative to the representation of the lyrics of the music track on the display. For example a vertical position of lyrics of the music track relative to a horizontal axis of the display corresponds to a pitch of the music track. A difference between pitch of the performance and notes of the music track is represented by a difference between the vertical position of the lyrics of the performance and the vertical position of the corresponding lyrics of the music track. A difference between a horizontal position of the lyrics of the performance and a horizontal position of the corresponding lyrics represents the tempo difference, which provides a feedback to the user that an error in a timing of the performance has occurred.
Abstract:
The invention consists of new ways of constructing a Measuring Matrices (MMs) including time deconvolution of Digital Fourier Transforms DFTs. Also, windowing functions specifically designed to facilitate time deconvolution may be used, and/or the DFTs may be performed in specific non-periodic ways to reduce artifacts and further facilitate deconvolution. These deconvolved DFTs may be used alone or correlated with other DFTs to produce a MM.
Abstract:
A machine-implemented method for computerized digital signal processing, comprising: obtaining a digital signal from data storage or from conversion of an analog signal; and determining, from the digital signal, measuring matrices. Each measuring matrix has a plurality of cells, each cell having an amplitude corresponding to the signal energy in a frequency bin for a time slice. Cells in each measuring matrix having maximum amplitudes along a time slice and/or frequency bin are identified as maximum cells. Maxima that coincide in time and frequency are identified and a correlated maxima matrix, called a "Precision Measuring Matrix" is constructed showing the coinciding maxima and the adjacent marked maxima are linked into partial chains. If only one MM is constructed, multiple types of maxima are identified to generate the Precision Measuring Matrix.