摘要:
A timbre creation method, system, and computer program product include performing a timbre analysis of a sound from an input source to generate a digital fingerprint of the sound, performing deep learning to create a patch that matches the digital fingerprint, and generating a second patch for a synthesizer which reproduces a timbre that complements the digital fingerprint based on the patch.
摘要:
A sound generating analog synthesizer that is comprised of potentiometers, a switch or switches and a set of patch jacks has a control system that can be operated in three modes, a manual mode, an automatic mode, and a guided mode; wherein manual mode allows potentiometer and switch positions as well as patch cable connections to be set by hand; wherein automatic mode, automatically sets patch connections as on or off, as well as set potentiometer positions and switch states with electromechanical or electrical devices; and wherein the guided mode provides at least one visual information on how to change the potentiometer positions, switch states and patch jack connections such that a previously obtained sound can be reproduced.
摘要:
An artificial intelligence song/music recommendation system and method is provided that allows music shoppers to discover new music. The system and method accomplish these tasks by analyzing a database of music in order to identify key similarities between different pieces of music, and then recommends pieces of music to a user depending upon their music preferences.
摘要:
The method of the present invention utilizes machine-learning techniques, particularly Support Vector Machines in combination with a neural network, to process a unique machine-learning enabled representation of the audio bitstream. Using this method, a classifying machine is able to autonomously detect characteristics of a piece of music, such as the artist or genre, and classify it accordingly. The method includes transforming digital time-domain representation of music into a frequency-domain representation, then dividing that frequency data into time slices, and compressing it into frequency bands to form multiple learning representations of each song. The learning representations that result are processed by a group of Support Vector Machines, then by a neural network, both previously trained to distinguish among a given set of characteristics, to determine the classification.
摘要:
Amplitude, phase and frequency of a sine wave to be generated are calculated on the basis of feature quantity s1 delivered to feature quantity detecting means (2), and are sent to initialization means (3). The initialization means (3) calculates first two points of the sine wave to send the points thus calculated to oscillator (sine wave generating means) (4) as initial value s4. The oscillator (4) sequentially calculates values of respective sample points of waveform by using recurrence formula in accordance with initial value or values instructed from the initialization means (3) to thereby generate a sine wave signal. Thus, sine wave generation is performed without performing modulo-addressing.
摘要:
A digital sampling instrument for multi-channel interpolatative playback of digital audio data stored in a waveform memory provides improved interpolation of musical sounds by use of a cache memory.
摘要:
Musical tones are produced according to song data basically by three steps. The first step converts the song data sequentially into control parameters. The control parameters are written into a parameter memory. Then, the second step generates waveform data by using the control parameters written in the parameter memory. The generated waveform data are written into a waveform memory, while the used control parameters are erased from the parameter memory to provide a vacant area. Lastly, the third step reads the waveform data sequentially from the waveform memory to produce the musical tones. Characterizingly, the second step of generating waveform data is executed dependently on progression of the third step of reading the waveform data. Further, the first step of converting the song data is executed independently from progression of the second step of generating waveform data as long as the parameter memory has the vacant area sufficient to store the control parameters converted from the song data.
摘要:
The present invention provides a method for editing digital audio information, such as musical material. Original musical parameters (302) are extracted and/or inputted from recorded original digital audio material (300). The original musical parameters (302) are then edited. The resulting edited musical parameters (304) are compared to the original musical parameters (302) to provide time varying control functions (308, 310, 312). The original digital audio material (300) is then processed with signal processing algorithms (314, 316, 318) which are controlled by the time varying control functions (308, 310, 312). This processing changes the original digital audio material (300) into new digital audio material (320) having musical characteristics which correspond to the edited musical parameters (304).
摘要:
An additive sound synthesis process for generating complex, realistic sounds is realized in a computationally efficient manner. In accordance with one aspect of the invention, polyphony is efficiently achieved by dosing the energy of a given partial between separate transform sums corresponding to different channels. In accordance with another aspect of the invention, noise is injected by randomly perturbing the phase of the sound, either on a per-partial basis or on a transform-sum basis. In the latter instance, the phase is perturbed in different regions of the spectrum to a degree determined by the amount of energy present in the respective regions of the spectrum. In accordance with yet another aspect of the invention, a transform sum representing a sound is processed in the transform domain to achieve with great economy effects achievable only at much greater expense outside the transform domain. Other transforms besides the Fourier transform may be used to advantage. For example, use of the Hartley transform produces comparable results but allows transforms to be computed at approximately twice the speed as the Fourier transform.
摘要:
In a closed wave guide network having a bidirectional signal transmitting channel section and a signal junction section, signal delay time is variably controlled by a first parameter group so as to control the resonance frequency characteristics of the wave guide network. A signal excitor is connected to the wave guide network so that an excited signal is supplied to the network. The excitation frequency of the excitor is controlled in accordance with a second parameter group. There are also provided a combination determination section which, in correspondence to the pitch of a tone to be generated, determines a combination of the first parameter group to be used in the wave guide network and the second parameter group to be used in the excitor, and a parameter generator which, in accordance with the combination determined by the combination determination section, generates and supplies individual parameters of the first and second parameter groups. The pitch of a tone to be generated is determined by a combination of the resonance characteristics of the wave guide network and the excitation frequency of the signal excitor.