Systems and methods for audio source separation include receiving a single-track audio input sample having an unknown mixture of audio signals generated from a plurality of audio sources, and separating one or more of the audio sources from the single-track audio input sample using a sequential audio source separation model. Separating one or more of the audio sources may include defining a processing recipe comprising a plurality of source separation processes configured to receive an audio input mixture and output one or more separated source signals and a remaining complement signal mixture, and processing the single-track audio input sample in accordance with the processing recipe to generate a plurality of audio stems separated from the unknown mixture of audio signals.

A sound processing system includes an electronic musical instrument and a sound processing apparatus communicable with the instrument. The instrument includes an audio signal generator that generates an audio signal according to a user performance on the electronic musical instrument, a first signal processor that performs first effect processing on the audio signal to generate a first processed audio signal, a first sound emitter that emits a first performance sound component based on at least one of the first processed audio signal or a second processed audio signal, and a first audio signal output that outputs the audio signal. The apparatus includes a first audio signal receiver that receives the audio signal output from the first audio signal output, in a state where the instrument is communicating with the apparatus, a second signal processor that performs second effect processing on the received audio signal, including removing a direct sound component from the received audio signal, to generate the second processed audio signal, and a second sound emitter that emits a second performance sound component based on the second processed audio signal. In the state where the instrument is communicating with the apparatus, the first signal processor changes the amount of the first effect processing to the generated audio signal in generating the first processed audio signal that is emitted by the first sound emitter, in a state where the audio signal is not output to the apparatus, or the first sound emitter emits the second performance sound component based on the second processed audio signal.

A wireless controller that allows a musician to wirelessly switch between audio effect presets, loops, and/or songs which are stored in a specialized audio/instrument cable or adapter. The wireless controller can be located in the same place as (or incorporated into) a digital guitar tuner on a guitar headstock allowing the musician to operate the wireless controller in a familiar location while switching between audio effect presets, loops, and/or songs by tapping on small buttons.

A control device (1) for controlling the sound of an electric musical instrument has a tread plate (2) and a signal generator (3). The tread plate (2) is mounted pivotally about a first axis (4a) and is mounted pivotally about a second axis (4b). The signal generator is configured such that it generates a first electrical signal for controlling the sound and a second electrical signal for controlling the sound, the first electrical signal being the result of a rotation of the tread plate (2) about the first axis (4a) and the second electrical signal being the result of a rotation of the tread plate (2) about the second axis (4b). A control system comprises a control device of this type and the electric musical instrument.

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.

A musical sound producing apparatus includes a plurality of keys, a sound production information generator that generates sound production information for producing a musical sound based on a first key operation on any key among the plurality of keys, a control information generator that generates control information for controlling, on the basis of a second key operation different from the first key operation, a mode of the musical sound produced on the basis of the first key operation, and a musical sound signal generator that generates a musical sound signal on the basis of the sound production information and the control information.

A social entertainment user interface operating on a wireless networked record session device capable of producing a live video and/or audio stream as if made in a vintage record booth. Record sessions are listened to and/or watched by a plurality of other social entertainment user interfaces operating on other networked listening/watching wireless networked devices. Video and audio filters emulate various altered looks and sounds. Record sessions are streamed live or near-live for other social entertainment user interfaces operating on other networked wireless devices to listen and/or watch, and passively and actively rated to dynamically enable watching of the most preferred record sessions.

A musical sound that is rich in amusement can be provided. A musical sound control device includes: a plurality of operators; a musical sound processing part configured to repeat a process of controlling a musical sound in each of a plurality of steps in accordance with control information set by the plurality of operators; and a control part configured to stop an operation of the musical sound processing part in a case in which the process of controlling a musical sound of the plurality of all the steps using the musical sound processing part has gone through one cycle in a case in which a predetermined condition is satisfied.

A fade device includes a processor that couples a crossfader to a mixer, the processor using crossfader input to apply an acceleration or a latency to an audio signal passing through a mixer.

The present disclosure provides a generation device having a plurality of operators that receive a user operation that causes generation of a sound. The generation device includes: at least one first operator arranged in a first region and configured to receive a first user operation that causes generation of a rhythm sound signal; at least one second operator arranged in a second region and configured to receive a second user operation that causes generation of a melody sound signal; and at least one third operator arranged in a third region and configured to receive a third user operation that causes a sound effect to be applied to a synthesized sound signal of the generated rhythm sound signal and the generated melody sound signal. The first region, the second region, and the third region are different regions of the generation device from each other.