Related papers: Small Tunes Transformer: Exploring Macro & Micro-L…
Symbolic music generation has seen rapid progress with artificial neural networks, yet remains underexplored in the biologically plausible domain of spiking neural networks (SNNs), where both standardized benchmarks and comprehensive…
We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…
Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets,…
Automatic music transcription converts audio recordings into symbolic representations, facilitating music analysis, retrieval, and generation. A musical note is characterized by pitch, onset, and offset in an audio domain, whereas it is…
Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them. Despite achievements in…
In music and speech, meaning is derived at multiple levels of context. Affect, for example, can be inferred both by a short sound token and by sonic patterns over a longer temporal window such as an entire recording. In this letter, we…
This paper explores the modeling method of polyphonic music sequence. Due to the great potential of Transformer models in music generation, controllable music generation is receiving more attention. In the task of polyphonic music, current…
For the tasks of automatic music emotion recognition, genre recognition, music recommendation it is helpful to be able to extract mode from any section of a musical piece as a perceived amount of major or minor mode (majorness) inside that…
A commonly-cited reason for the poor performance of automatic chord estimation (ACE) systems within music information retrieval (MIR) is that non-chord tones (i.e., notes outside the supporting harmony) contribute to error during the…
Automatically generating symbolic music-music scores tailored to specific human needs-can be highly beneficial for musicians and enthusiasts. Recent studies have shown promising results using extensive datasets and advanced transformer…
We present a neural sequence model designed specifically for symbolic music. The model is based on a learned edit distance mechanism which generalises a classic recursion from computer sci- ence, leading to a neural dynamic program. Re-…
We present a sequential transfer learning framework for transformers on functional Magnetic Resonance Imaging (fMRI) data and demonstrate its significant benefits for decoding musical timbre. In the first of two phases, we pre-train our…
We introduce a structure-aware approach for symbolic piano accompaniment that decouples high-level planning from note-level realization. A lightweight transformer predicts an interpretable, per-measure style plan conditioned on…
Deep Learning models have shown very promising results in automatically composing polyphonic music pieces. However, it is very hard to control such models in order to guide the compositions towards a desired goal. We are interested in…
Predictive models for music are studied by researchers of algorithmic composition, the cognitive sciences and machine learning. They serve as base models for composition, can simulate human prediction and provide a multidisciplinary…
We introduce a novel playlist generation algorithm that focuses on the quality of transitions using a recurrent neural network (RNN). The proposed model assumes that optimal transitions between tracks can be modelled and predicted by…
The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…
This paper approaches the problem of separating the notes from a quantized symbolic music piece (e.g., a MIDI file) into multiple voices and staves. This is a fundamental part of the larger task of music score engraving (or score…
High-level musical qualities (such as emotion) are often abstract, subjective, and hard to quantify. Given these difficulties, it is not easy to learn good feature representations with supervised learning techniques, either because of the…
Conventional music structure analysis algorithms aim to divide a song into segments and to group them with abstract labels (e.g., 'A', 'B', and 'C'). However, explicitly identifying the function of each segment (e.g., 'verse' or 'chorus')…