Projects per year
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.
|Title of host publication||ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||5|
|Publication status||E-pub ahead of print - 13 May 2021|
- time-frequency analysis
- channel capacity
- speech recognition
- audio recognition
- action recognition
- multi-stream networks
FingerprintDive into the research topics of 'SLOW-FAST AUDITORY STREAMS FOR AUDIO RECOGNITION'. Together they form a unique fingerprint.
- 1 Active