Improvement and Cross-Domain Evaluation of SlowFast Networks

Kumar R, Grollmisch S, Abeßer J. Improvement and Cross-Domain Evaluation of SlowFast Networks. In: 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio. Audio Engineering Society; 2025. Paper 22. Available from: https://aes.org/publications/elibrary-page/?id=23011

@inproceedings{Kumar2025_23011,
  author = {Kumar, Ravi and Grollmisch, Sascha and Abeßer, Jakob},
  title = {{Improvement and Cross-Domain Evaluation of SlowFast Networks}},
  booktitle = {2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio},
  note = {Paper 22},
  year = {2025},
  month = sep,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23011}
}

TY  - CPAPER
TI  - Improvement and Cross-Domain Evaluation of SlowFast Networks
AU  - Kumar, Ravi
AU  - Grollmisch, Sascha
AU  - Abeßer, Jakob
T2  - 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
M1  - Paper 22
PY  - 2025
DA  - 2025/09/02
UR  - https://aes.org/publications/elibrary-page/?id=23011
PB  - Audio Engineering Society
LA  - en
AB  - Audio classification requires robust models which can capture both transient events and long-duration patterns. This poses a challenge for common single-stream convolutional neural networks that process short- and long-term events in a uniform fashion using the same kernels. Inspired by the dual-stream processing of the human auditory system, SlowFast networks separate temporal and spectral analysis into parallel pathways. In this paper, we propose several enhancements to the SlowFast network, implementing uniform separable convolutions on both the slow and fast pathways to streamline the architecture and improve efficiency, while also introducing a novel lightweight model variant with a 92 % parameter reduction. We perform a comprehensive cross-domain evaluation using eight datasets that cover speech, environmental sounds, industrial sounds, and bioacoustic sounds. The enhanced SlowFast network surpasses the original SlowFast network as well as the MobileNetV3 single-stream baseline, especially for single-label tasks, while remaining competitive in multi-label tasks. The study highlights the potentialof dual-stream architectures and underscores the importance of architectural design for audio classification.
ER  -