A computer system for enabling generation/controlling/modification of sound elements is provided. A computer program defines a sound engine. The sound engine includes or is linked to one or more musical composition interfaces that enable one or more users to access a music generator/controller/modifier utility (“music generator”), so as to graphically map one or more musical notes by tracing one or more Bezier paths defined that are processable by the music generator so as to define five fundamental note qualities: Tone, pitch, volume, applied effects and duration. The music generator enables user manipulation of the Bezier paths, including touch input modification of the paths (e.g. dragging, forming etc.) that modify fundamental qualities of the corresponding note.

A storage medium storing a musical performance program and a musical performance device are provided. A musical sound is output through a clicking operation performed on an operation button, and a tone parameter is changed through a dragging operation. A parameter display part 6a is displayed on the operation button. When the musical sound is output through a clicking operation performed on the operation button, a user can recognize a state of the tone parameter of the output musical sound in advance through the parameter display part. Since the tone parameter set through a dragging operation performed on the operation button is reflected to the parameter display part, the tone parameter is recognized without looking away from the operation button.

A system is provided for editing an audio file. The system displays, on an electronic device, a piano roll. The system receives a user input to cut a segment of the piano roll. The segment of the piano roll includes a respective tone that extends across both sides of the segment of the piano roll, such that the respective tone includes: a first portion of the respective tone that precedes the segment of the piano roll; and a second portion of the respective tone that follows the segment of the piano roll. In response to the user input to cut the segment of the piano roll, the system cuts the segment from the piano roll and, without user intervention, concatenate the first portion of the respective tone with the second portion of the respective tone.

Audio translation system includes a feature extractor and a style transfer machine learning model. The feature extractor generates for each of a plurality of source voice files one or more source voice parameters encoded as a collection of source feature vectors, and generates for each of a plurality of target voice files one or more target voice parameters encoded as a collection of target feature vectors. The style transfer machine learning model trained on the collection of source feature vectors for the plurality of source voice files and the collection of target feature vectors for the plurality of target voice files to generate a style transformed feature vector.

Systems and methods for generating a visual color display of audio-file data are provided. The system includes a processor that performs a method including receiving audio-file data; generating filtered-audio data by processing the audio-file data by frequency-band filters. The frequency band filters have different frequency bands. The method includes generating one or more waveforms corresponding to the filtered-audio data and displaying the waveforms superimposed in unique color relative to one another. The method includes downsampling the waveforms. The method includes processing the waveforms through an envelope detector. The method includes processing the waveforms through an expander and applying a gain factor. The waveforms have transparency levels at sections that are proportional or inversely proportional to amplitudes at the sections.

Systems and methods directed to combining audio tracks are provided. More specifically, a first audio track and a second audio track are received. The first audio track is separated into a vocal component and one or more accompaniment components. The second audio track is separated into a vocal component and one or more accompaniment components. A structure of the first audio track and a structure of the second audio track are determined. The first audio track and the second audio track are aligned based on the determined structures of the tracks. The vocal component of the first audio track is stretched to match a tempo of the second audio track. The stretched vocal component of the first audio track is added to the one or more accompaniment components of the second audio track.

Systems and methods for generating a playback-information display during time compression or expansion of an audio signal are provided. The system includes a processor that performs a method including displaying a first remaining playback-time associated with an audio file; adjusting the playback speed of the audio file during playback of the audio file; and, in response to the playback speed being adjusted, automatically displaying a second remaining playback-time associated with the audio file during playback of the audio file.

The present technology relates to a signal processing device, a signal processing method, and a program that enable intuitive operation of sound.

The signal processing device includes an acquisition unit that acquires a sensing value indicating a motion of a predetermined portion of a body of a user or motion of an instrument, and a control unit that performs non-linear acoustic processing on an acoustic signal according to the sensing value. The present technology can be applied to an acoustic reproduction system.

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.

Audio translation system includes a feature extractor and a style transfer machine learning model. The feature extractor generates for each of a plurality of source voice files one or more source voice parameters encoded as a collection of source feature vectors, and generates for each of a plurality of target voice files one or more target voice parameters encoded as a collection of target feature vectors. The style transfer machine learning model trained on the collection of source feature vectors for the plurality of source voice files and the collection of target feature vectors for the plurality of target voice files to generate a style transformed feature vector.