Machine learningMachine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.
Electronic musical instrumentAn electronic musical instrument or electrophone is a musical instrument that produces sound using electronic circuitry. Such an instrument sounds by outputting an electrical, electronic or digital audio signal that ultimately is plugged into a power amplifier which drives a loudspeaker, creating the sound heard by the performer and listener. An electronic instrument might include a user interface for controlling its sound, often by adjusting the pitch, frequency, or duration of each note.
Keyboard instrumentA keyboard instrument is a musical instrument played using a keyboard, a row of levers that are pressed by the fingers. The most common of these are the piano, organ, and various electronic keyboards, including synthesizers and digital pianos. Other keyboard instruments include celestas, which are struck idiophones operated by a keyboard, and carillons, which are usually housed in bell towers or belfries of churches or municipal buildings. Today, the term keyboard often refers to keyboard-style synthesizers.
Musical instrumentA musical instrument is a device created or adapted to make musical sounds. In principle, any object that produces sound can be considered a musical instrument—it is through purpose that the object becomes a musical instrument. A person who plays a musical instrument is known as an instrumentalist. The history of musical instruments dates to the beginnings of human culture. Early musical instruments may have been used for rituals, such as a horn to signal success on the hunt, or a drum in a religious ceremony.
Live electronic musicLive electronic music (also known as live electronics) is a form of music that can include traditional electronic sound-generating devices, modified electric musical instruments, hacked sound generating technologies, and computers. Initially the practice developed in reaction to sound-based composition for fixed media such as musique concrète, electronic music and early computer music. Musical improvisation often plays a large role in the performance of this music.
Percussion instrumentA percussion instrument is a musical instrument that is sounded by being struck or scraped by a beater including attached or enclosed beaters or rattles struck, scraped or rubbed by hand or struck against another similar instrument. Excluding zoomusicological instruments and the human voice, the percussion family is believed to include the oldest musical instruments. In spite of being a very common term to designate instruments, and to relate them to their players, the percussionists, percussion is not a systematic classificatory category of instruments, as described by the scientific field of organology.
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.
Classical musicClassical music generally refers to the art music of the Western world, considered to be distinct from Western folk music or popular music traditions. It is sometimes distinguished as Western classical music, as the term "classical music" also applies to non-Western art music. Classical music is often characterized by formality and complexity in its musical form and harmonic organization, particularly with the use of polyphony.
String instrumentString instruments, stringed instruments, or chordophones are musical instruments that produce sound from vibrating strings when a performer plays or sounds the strings in some manner. Musicians play some string instruments by plucking the strings with their fingers or a plectrum—and others by hitting the strings with a light wooden hammer or by rubbing the strings with a bow. In some keyboard instruments, such as the harpsichord, the musician presses a key that plucks the string.
Brass instrumentA brass instrument is a musical instrument that produces sound by sympathetic vibration of air in a tubular resonator in sympathy with the vibration of the player's lips. Brass instruments are also called labrosones or labrophones, from Latin and Greek elements meaning 'lip' and 'sound'. There are several factors involved in producing different pitches on a brass instrument.
Generative pre-trained transformerGenerative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.
Foundation modelsA foundation model (also called base model) is a large machine learning (ML) model trained on a vast quantity of data at scale (often by self-supervised learning or semi-supervised learning) such that it can be adapted to a wide range of downstream tasks. Foundation models have helped bring about a major transformation in how artificial intelligence (AI) systems are built, such as by powering prominent chatbots and other user-facing AI.
Large language modelA large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.
Computer musicComputer music is the application of computing technology in music composition, to help human composers create new music or to have computers independently create music, such as with algorithmic composition programs. It includes the theory and application of new and existing computer software technologies and basic aspects of music, such as sound synthesis, digital signal processing, sound design, sonic diffusion, acoustics, electrical engineering, and psychoacoustics.
GuitarThe guitar is a fretted musical instrument that typically has six strings. It is usually held flat against the player's body and played by strumming or plucking the strings with the dominant hand, while simultaneously pressing selected strings against frets with the fingers of the opposite hand. A plectrum or individual finger picks may also be used to strike the strings. The sound of the guitar is projected either acoustically, by means of a resonant chamber on the instrument, or amplified by an electronic pickup and an amplifier.
Recording studioA recording studio is a specialized facility for recording and mixing of instrumental or vocal musical performances, spoken words, and other sounds. They range in size from a small in-home project studio large enough to record a single singer-guitarist, to a large building with space for a full orchestra of 100 or more musicians. Ideally, both the recording and monitoring (listening and mixing) spaces are specially designed by an acoustician or audio engineer to achieve optimum acoustic properties (acoustic isolation or diffusion or absorption of reflected sound echoes that could otherwise interfere with the sound heard by the listener).
Steel guitarA steel guitar (kīkākila) is any guitar played while moving a steel bar or similar hard object against plucked strings. The bar itself is called a "steel" and is the source of the name "steel guitar". The instrument differs from a conventional guitar in that it is played without using frets; conceptually, it is somewhat akin to playing a guitar with one finger (the bar). Known for its portamento capabilities, gliding smoothly over every pitch between notes, the instrument can produce a sinuous crying sound and deep vibrato emulating the human singing voice.
Language modelA language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.
Record producerA record producer is a music recording project's overall supervisor whose responsibilities can involve a range of creative and technical leadership roles. Typically the job involves hands-on oversight of recording sessions: ensuring artists deliver acceptable performances, supervising the technical engineering of the recording, and coordinating the production team and process. The producer's involvement in a musical project can vary in depth and scope. Sometimes in popular genres the producer may create the recording's entire sound and structure.
Transformer (machine learning model)A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.
