Audio Mamba: Bidirectional State Space Model for Audio Representation Learning
Research paper by Mehmet Hamza Erol and collaborators. Published 2024-06-05. Topics: Audio Spectrogram Transformers (ASTs), self-attention, quadratic scaling, state state models (SSMs), Audio Mamba (AuM).
Resource information
- Authors
- Mehmet Hamza Erol, Arda Senocak, Jiu Feng, Joon Son Chung
- Research topics
- Audio Spectrogram Transformers (ASTs), self-attention, quadratic scaling, state state models (SSMs), Audio Mamba (AuM)
- Publication date
- 2024-06-05
- Publication
- arXiv
- Last record update
- Nov 3, 2026