Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
SynthesizerA synthesizer (also spelled synthesiser) is an electronic musical instrument that generates audio signals. Synthesizers typically create sounds by generating waveforms through methods including subtractive synthesis, additive synthesis and frequency modulation synthesis. These sounds may be altered by components such as filters, which cut or boost frequencies; envelopes, which control articulation, or how notes begin and end; and low-frequency oscillators, which modulate parameters such as pitch, volume, or filter characteristics affecting timbre.
Electronic musicElectronic music is a genre of music that employs electronic musical instruments, digital instruments, or circuitry-based music technology in its creation. It includes both music made using electronic and electromechanical means (electroacoustic music). Pure electronic instruments depended entirely on circuitry-based sound generation, for instance using devices such as an electronic oscillator, theremin, or synthesizer. Electromechanical instruments can have mechanical parts such as strings, hammers, and electric elements including magnetic pickups, power amplifiers and loudspeakers.
Digital synthesizerA digital synthesizer is a synthesizer that uses digital signal processing (DSP) techniques to make musical sounds. This in contrast to older analog synthesizers, which produce music using analog electronics, and samplers, which play back digital recordings of acoustic, electric, or electronic instruments. Some digital synthesizers emulate analog synthesizers; others include sampling capability in addition to digital synthesis. The very earliest digital synthesis experiments were made with computers, as part of academic research into sound generation.
Analog modeling synthesizerAn analog modeling synthesizer is a synthesizer that generates the sounds of traditional analog synthesizers using digital signal processing components and software algorithms. Analog modeling synthesizers simulate the behavior of the original electronic circuitry in order to digitally replicate their tone. This method of synthesis is also referred to as virtual analog or VA. Analog modeling synthesizers can be more reliable than their true analog counterparts since the oscillator pitch is ultimately maintained by a digital clock, and the digital hardware is typically less susceptible to temperature changes.
Software synthesizerA software synthesizer or softsynth is a computer program that generates digital audio, usually for music. Computer software that can create sounds or music is not new, but advances in processing speed now allow softsynths to accomplish the same tasks that previously required the dedicated hardware of a conventional synthesizer. Softsynths may be readily interfaced with other music software such as music sequencers typically in the context of a digital audio workstation.
Music educationMusic education is a field of practice in which educators are trained for careers as elementary or secondary music teachers, school or music conservatory ensemble directors. Music education is also a research area in which scholars do original research on ways of teaching and learning music. Music education scholars publish their findings in peer-reviewed journals, and teach undergraduate and graduate education students at university education or music schools, who are training to become music teachers.
Generative modelIn statistical classification, two main approaches are called the generative approach and the discriminative approach. These compute classifiers by different approaches, differing in the degree of statistical modelling. Terminology is inconsistent, but three major types can be distinguished, following : A generative model is a statistical model of the joint probability distribution on given observable variable X and target variable Y; A discriminative model is a model of the conditional probability of the target Y, given an observation x; and Classifiers computed without using a probability model are also referred to loosely as "discriminative".
Music technology (electronic and digital)Digital music technology encompasses digital instruments, computers, electronic effects units, software, or digital audio equipment by a performer, composer, sound engineer, DJ, or record producer to produce, perform or record music. The term refers to electronic devices, instruments, computer hardware, and software used in performance, playback, recording, composition, mixing, analysis, and editing of music.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
