IEEE Signal Processing Letters · 2024 · 35 citations · 16 references
ComputingComputer ScienceComputer VisionMachine LearningVisual AttentionDeep LearningPattern RecognitionRepresentation LearningSpeech RecognitionAudio ClassificationTransformer ModelsTransformer-based Classification
Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic self-attention cost presents an appealing direction. Recently, state space models (SSMs), such as Mamba, have demonstrated potential in language and vision tasks in this regard. In this study, we explore whether reliance on self-attention is necessary for audio classification tasks. By introducing Audio Mamba (AuM), the first self-attention-free, purely SSM-based model for audio classification, we aim to address this question. We evaluate AuM on various audio datasets - comprising six different benchmarks - where it achieves comparable or better performance compared to well-established AST model.
16
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
AST: Audio Spectrogram Transformer
Yuan Gong, Yu-An Chung, James Glass · 2021 · 989 citations
Voxceleb: Large-scale speaker verification in the wild
Arsha Nagrani, Joon Son Chung, Weidi Xie et al. · Computer Speech & Language · 2019 · 654 citations · Full text