paper-with-me

Papers

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 SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We address this by integrating the encoder-decoder architecture from Masked Autoencoders are Scalable Vision Learners (MAE) into the SSAST, where a deep encoder operates on only unmasked input, and a shallow decoder operates on encoder outputs and mask tokens. We find that MAE-like pretraining can provide a 3x speedup and 2x memory usage reduction over the vanilla SSAST using current audio pretraining strategies with ordinary model and input sizes. When fine-tuning on downstream tasks, which only uses the encoder, we find that our approach outperforms the SSAST on a variety of downstream tasks. We further conduct comprehensive evaluations into different strategies of pretraining and explore differences in MAE-style pretraining between the visual and audio domains.

📄 PDF Abstract BibTeX arXiv:2203.16691

Code (2)

AlanBaade/MAE-AST-Public 공식 구현 pytorch
rishikksh20/AudioMAE-pytorch pytorch

Tasks

Audio ClassificationDecoder

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

TVLT: Textless Vision-Language Transformer

2022-09-28 · Zineng Tang, Jaemin Cho, Yixin Nie, Mohit Bansal

In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specif…

Automatic Speech Recognition (ASR)Image RetrievalMultimodal Sentiment AnalysisQuestion Answering+5

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

Diffusion Models as Masked Audio-Video Learners

2023-10-05 · Elvis Nunez, Yanzi Jin, Mohammad Rastegari, Sachin Mehta 외

Over the past several years, the synchronization between audio and visual signals has been leveraged to learn richer audio-visual representations. Aided by the large availability of unlabeled videos, many unsupervised tr…

Audio ClassificationContrastive Learning

AudioMAE++: learning better masked audio representations with SwiGLU FFNs

2025-07-14 · Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan arxiv

Masked Autoencoders (MAEs) trained on audio spectrogram patches have emerged as a prominent approach for learning self-supervised audio representations. While several recent papers have evaluated key aspects of training …

Audio Classification