Official Code for CrossMamba in "Cross-attention Inspired Selective State Space Models for Target Sound Extraction", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, available at https://arxiv.org/abs/2409.04803.

This code is adapted from the original open source repository at https://github.com/state-spaces/mamba. Thanks for the open source.

The original Mamba is needed to be installed in advance. Requirements are listed in https://github.com/state-spaces/mamba.

python example.py