MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCCF none

Sep 29, 2023

08/2022 – 05/2023

Supervised by Dr Emmanouil Benetos, Centre for Digital Music, Queen Mary University of London

  • Built self-supervised learning systems, acquiring 50k+ downloading of checkpoints on Huggingface.
  • Replaced the pseudo-tag from MFCCs to Chroma music features for harmonic information.
  • Utilising deep features like Encodec instead of k-means for scaling up models to 1 B parameters.
MIR Deep Learning SSL
Avatar
马英浩 (Nicolaus) MA Yinghao
PhD Student in AI & Music

MA Yinghao, PhD student in C4DM, QMUL. Research interests include music information retireval, self-supervised learning, music-related multimodal machine learning, and audio signal processing and matter.

Related

Publications

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCCF none

Abstract: Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale …
Project

On the effectiveness of speech self-supervised learning for musicCCF none

Abstract: Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. …
Project

Large-Scale Pretrained Model for Self-Supervised Music Audio Representation Learning

Project

Map-music2vec: A simple and effective baseline for self-supervised music audio representation learning

Abstract: The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL). However, it …
Project