paper-with-me

Papers

Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation

2022-04-26 · Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Kunio Kashino

Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example, typical audio contrastive learning uses temporal relationships among input sounds to create training signals, whereas some methods use a difference among input views created by data augmentations. However, these training signals do not provide information derived from the intact input sound, which we think is suboptimal for learning representation that describes the input as it is. In this paper, we seek to learn audio representations from the input itself as supervision using a pretext task of auto-encoding of masked spectrogram patches, Masked Spectrogram Modeling (MSM, a variant of Masked Image Modeling applied to audio spectrogram). To implement MSM, we use Masked Autoencoders (MAE), an image self-supervised learning method. MAE learns to efficiently encode the small number of visible patches into latent representations to carry essential information for reconstructing a large number of masked patches. While training, MAE minimizes the reconstruction error, which uses the input as training signal, consequently achieving our goal. We conducted experiments on our MSM using MAE (MSM-MAE) models under the evaluation benchmark of the HEAR 2021 NeurIPS Challenge. Our MSM-MAE models outperformed the HEAR 2021 Challenge results on seven out of 15 tasks (e.g., accuracies of 73.4% on CREMA-D and 85.8% on LibriCount), while showing top performance on other tasks where specialized models perform better. We also investigate how the design choices of MSM-MAE impact the performance and conduct qualitative analysis of visualization outcomes to gain an understanding of learned representations. We make our code available online.

📄 PDF Abstract BibTeX arXiv:2204.12260

Code (1)

nttcslab/msm-mae 공식 구현 pytorch

Tasks

Contrastive LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

MAE 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Masked Autoencoders that Listen

2022-07-13 · Po-Yao Huang, Hu Xu, Juncheng Li, Alexei Baevski 외

This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE fi…

Audio ClassificationDecoderRepresentation LearningSpeaker Identification

An overview of neural architectures for self-supervised audio representation learning from masked spectrograms

2025-09-23 · Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan arxiv

In recent years, self-supervised learning has amassed significant interest for training deep neural representations without labeled data. One such self-supervised learning approach is masked spectrogram modeling, where t…

Self-Supervised LearningRepresentation LearningAudio Classification

MAE-AST: Masked Autoencoding Audio Spectrogram Transformer

2022-03-30 · Alan Baade, Puyuan Peng, David Harwath

In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the …

Audio ClassificationDecoder

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond

2022-07-30 · Chaoning Zhang, Chenshuang Zhang, Junha Song, John Seon Keun Yi 외

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, genera…

Contrastive LearningDenoisingSelf-Supervised Learning

Quantum Masked Autoencoders for Vision Learning

2025-11-21 · Emma Andrews, Prabhat Mishra arxiv

Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in t…