Bi-WKV

AudioRWKV: Efficient and Stable Bidirectional RWKV for Audio Pattern Recognition

Announce Type: replace Abstract: Recently, Transformers (e.g., Audio Spectrogram Transformers, AST) and state-space models (e.g., Audio Mamba, AuM) have achieved remarkable progress in audio modeling. However, the O(L^2) computational complexity of the Transformer architecture hinders efficient long-sequence processing, while the Mamba architecture tends to become unstable when scaling parameters and data.