A digital-to-analog conversion device which performs integration processing for integrating a difference between an input signal and a first return signal generated based on the input signal, and outputting an integration result, first quantization processing for quantizing the integration result, and outputting a first quantization signal, first return signal output processing for outputting the first return signal by adding to the first quantization signal a correction value delay signal acquired by a correction value signal outputted based on the integration result being delayed, and output processing for outputting output signals including a signal whose pulse width is asymmetrical to center of a processing period, based on the first quantization signal, in which the correction value signal includes a signal indicating a correction value for correcting a difference between a center of the pulse width asymmetrical to the center of the processing period and the center of the processing period.

A digital-to-analog conversion device which performs integration processing for integrating a difference between an input signal and a first return signal generated based on the input signal, and outputting an integration result, first quantization processing for quantizing the integration result, and outputting a first quantization signal, first return signal output processing for outputting the first return signal by adding to the first quantization signal a correction value delay signal acquired by a correction value signal outputted based on the integration result being delayed, and output processing for outputting output signals including a signal whose pulse width is asymmetrical to center of a processing period, based on the first quantization signal, in which the correction value signal includes a signal indicating a correction value for correcting a difference between a center of the pulse width asymmetrical to the center of the processing period and the center of the processing period.

A voice synthesis method according to an embodiment includes altering a series of synthesis spectra in a partial period of a synthesis voice based on a series of amplitude spectrum envelope contours of a voice expression to obtain a series of altered spectra to which the voice expression has been imparted, and synthesizing a series of voice samples to which the voice expression has been imparted, based on the series of altered spectra.

A method analyzes a reference signal representing a sound in each of analysis periods to obtain a series of phase spectra and a series of amplitude spectra over the analysis periods; adjusts, for each respective analysis period, phases of each harmonic component in a respective phase spectrum to be a target value at a pitch mark corresponding to the respective analysis period; synthesizes a first sound signal over the analysis periods based on the adjusted series of phase spectra of the reference signal and the obtained series of amplitude spectra of the reference signal; prepares training data including first control data representing of generative conditions of the reference signal and the first sound signal synthesized from the reference signal; and establishes, through machine learning using the training data, the generative model that generates a second sound signal based on second control data representing generative conditions of the second sound signal.

A method analyzes a reference signal representing a sound in each of analysis periods to obtain a series of phase spectra and a series of amplitude spectra over the analysis periods; adjusts, for each respective analysis period, phases of each harmonic component in a respective phase spectrum to be a target value at a pitch mark corresponding to the respective analysis period; synthesizes a first sound signal over the analysis periods based on the adjusted series of phase spectra of the reference signal and the obtained series of amplitude spectra of the reference signal; prepares training data including first control data representing of generative conditions of the reference signal and the first sound signal synthesized from the reference signal; and establishes, through machine learning using the training data, the generative model that generates a second sound signal based on second control data representing generative conditions of the second sound signal.

According to an embodiment, there is provided a system and method for automatically generating a complete music work from a partially completed work provided by a user. One approach uses an artificial intelligence (AI) engine that is trained by creating incomplete works from a database of complete works and then instructing the AI to complete the incomplete works. A comparison is made between the completed works and the originals to determine the effectiveness of the training process. After the AI is trained, it is applied to the user's incomplete work to produce a final music item.

A sound source for an electronic percussion instrument and sound production control method thereof are provided. An electronic drum sound source device performs a weighting operation on four pieces of waveform information (pitch envelope, amplitude envelope, start phase) stored in a waveform table according to the beating conditions (hitting point position, velocity) based on the output from a struck sensor of an electronic drum pad. The electronic drum sound source device creates a sine wave on the basis of the waveform information whereon the weighting operation was performed, and generates musical sounds (sounds of percussion instrument) by synthesizing the sine wave with the waveforms of residual waveform data whereon the weighting operation was performed. The sine wave is not synthesized with waveform data other than the residual waveform data, and thus consistent musical sounds with no phase interference can be reproduced.

A sound source for an electronic percussion instrument and sound production control method thereof are provided. An electronic drum sound source device performs a weighting operation on four pieces of waveform information (pitch envelope, amplitude envelope, start phase) stored in a waveform table according to the beating conditions (hitting point position, velocity) based on the output from a struck sensor of an electronic drum pad. The electronic drum sound source device creates a sine wave on the basis of the waveform information whereon the weighting operation was performed, and generates musical sounds (sounds of percussion instrument) by synthesizing the sine wave with the waveforms of residual waveform data whereon the weighting operation was performed. The sine wave is not synthesized with waveform data other than the residual waveform data, and thus consistent musical sounds with no phase interference can be reproduced.

Musical catalog amplification services that leverage or deploy a computer-based musical composition system are described. The computer-based musical composition system employs algorithms and, optionally, artificial intelligence to generate new music based on analyses of existing music. The new music may be wholly distinctive from, or may include musical variations of, the existing music. Rights in the new music generated by the computer-based musical composition system are granted to the rights holder(s) of the existing music. In this way, the musical catalog(s) of the rights holder(s) is/are amplified to include additional music assets. The computer-based musical composition system may be tuned so that the new music sounds more like, or less like, the existing music of the rights holder(s). Revenues generated from the new music are shared between the musical catalog amplification service provider and the rights holder(s).

Computer-based systems, devices, and methods for assigning mood labels to musical compositions are described. A mood classifier is trained based on mood-labeled musically-coherent segments of musical compositions and subsequently applied to automatically assign mood labels to musically-coherent segments of musical compositions. In both cases, the musically-coherent segments are generated using automated segmentation algorithms.