Search Results for author:
Found 16 papers, 13 papers with code
Continuous diffusion for categorical data
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement.
The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling
We call this system the Chamber Ensemble Generator (CEG), and use it to generate a large dataset of chorales from four different chamber ensembles (CocoChorales).
Multi-instrument Music Synthesis with Spectrogram Diffusion
An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes.
Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$
Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves.
General-purpose, long-context autoregressive modeling with Perceiver AR
Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression.
Ranked #35 on
Language Modelling
on WikiText-103
MT3: Multi-Task Multitrack Music Transcription
Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding.
Ranked #2 on
Music Transcription
on Slakh2100
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Sequence-to-Sequence Piano Transcription with Transformers
Automatic Music Transcription has seen significant progress in recent years by training custom deep neural networks on large datasets.
Symbolic Music Generation with Diffusion Models
Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio.
Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset
We introduce the Expanded Groove MIDI dataset (E-GMD), an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed velocity annotations.
Encoding Musical Style with Transformer Autoencoders
We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models.
The Bach Doodle: Approachable music composition with machine learning at scale
To make music composition more approachable, we designed the first AI-powered Google Doodle, the Bach Doodle, where users can create their own melody and have it harmonized by a machine learning model Coconet (Huang et al., 2017) in the style of Bach.
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
Generating musical audio directly with neural networks is notoriously difficult because it requires coherently modeling structure at many different timescales.
Music Transformer
This is impractical for long sequences such as musical compositions since their memory complexity for intermediate relative information is quadratic in the sequence length.
Ranked #3 on
Music Modeling
on JSB Chorales
Learning a Latent Space of Multitrack Measures
Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem.
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data.
Onsets and Frames: Dual-Objective Piano Transcription
We advance the state of the art in polyphonic piano music transcription by using a deep convolutional and recurrent neural network which is trained to jointly predict onsets and frames.
