# Slow-Fast Auditory Streams For Audio Recognition

arXiv: https://arxiv.org/abs/2103.03516 · HTML: https://mlsanity.com/paper/2103.03516/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [SoundNet: Learning Sound Representations from Unlabeled Video](https://mlsanity.com/paper/1610.09001/) (2016)
- [Audiovisual SlowFast Networks for Video Recognition](https://mlsanity.com/paper/2001.08740/) (2020)
- [Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification](https://mlsanity.com/paper/1608.04363/) (2016)
- [The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1907.01803/) (2019)
- [Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks](https://mlsanity.com/paper/1706.07156/) (2017)
- [Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation](https://mlsanity.com/paper/2007.08389/) (2020)
- [State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions](https://mlsanity.com/paper/1910.00716/) (2019)
- [Timbre Analysis of Music Audio Signals with Convolutional Neural Networks](https://mlsanity.com/paper/1703.06697/) (2017)
- [Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling](https://mlsanity.com/paper/1907.06639/) (2019)
- [Multi-stream Network With Temporal Attention For Environmental Sound Classification](https://mlsanity.com/paper/1901.08608/) (2019)
- [Acoustic Features Fusion using Attentive Multi-channel Deep Architecture](https://mlsanity.com/paper/1811.00936/) (2018)

## Built on by (most cited first, 30 of 56)

- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [HD-EPIC: A Highly-Detailed Egocentric Video Dataset](https://mlsanity.com/paper/2502.04144/) (2025)
- [MAViL: Masked Audio-Video Learners](https://mlsanity.com/paper/2212.08071/) (2022)
- [PolyViT: Co-training Vision Transformers on Images, Videos and Audio](https://mlsanity.com/paper/2111.12993/) (2021)
- [Audiovisual Masked Autoencoders](https://mlsanity.com/paper/2212.05922/) (2022)
- [PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer](https://mlsanity.com/paper/2302.03548/) (2023)
- [Epic-Sounds: A Large-scale Dataset of Actions That Sound](https://mlsanity.com/paper/2302.00646/) (2023)
- [With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition](https://mlsanity.com/paper/2111.01024/) (2021)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Supervised and Unsupervised Learning of Audio Representations for Music Understanding](https://mlsanity.com/paper/2210.03799/) (2022)
- [UAVM: Towards Unifying Audio and Visual Models](https://mlsanity.com/paper/2208.00061/) (2022)
- [The iNaturalist Sounds Dataset](https://mlsanity.com/paper/2506.00343/) (2025)
- [Multiscale Audio Spectrogram Transformer for Efficient Audio Classification](https://mlsanity.com/paper/2303.10757/) (2023)
- [HeAR -- Health Acoustic Representations](https://mlsanity.com/paper/2403.02522/) (2024)
- [TIM: A Time Interval Machine for Audio-Visual Action Recognition](https://mlsanity.com/paper/2404.05559/) (2024)
- [Zorro: the masked multimodal transformer](https://mlsanity.com/paper/2301.09595/) (2023)
- [SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos](https://mlsanity.com/paper/2404.05206/) (2024)
- [MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization](https://mlsanity.com/paper/2203.07086/) (2022)
- [SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition](https://mlsanity.com/paper/2204.04796/) (2022)
- [Harnessing Temporal Causality for Advanced Temporal Action Detection](https://mlsanity.com/paper/2407.17792/) (2024)
- [Breaking the Encoder Barrier for Seamless Video-Language Understanding](https://mlsanity.com/paper/2503.18422/) (2025)
- [TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision](https://mlsanity.com/paper/2506.09445/) (2025)
- [Exploring Missing Modality in Multimodal Egocentric Datasets](https://mlsanity.com/paper/2401.11470/) (2024)
- [V-SlowFast Network for Efficient Visual Sound Separation](https://mlsanity.com/paper/2109.08867/) (2021)
- [Egocentric zone-aware action recognition across environments](https://mlsanity.com/paper/2409.14205/) (2024)
- [Explore the Limits of Omni-modal Pretraining at Scale](https://mlsanity.com/paper/2406.09412/) (2024)

## Abstract (arXiv)

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state-of-the-art results on both.