{"total":40,"rows":[{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2411.10027","title":"XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection","created":"2024-11-15","cited_by_count":30,"area":"ssm"},{"id":"2407.09732","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","created":"2024-07-13","cited_by_count":23,"area":"ssm"},{"id":"2409.07273","title":"Rethinking Mamba in Speech Processing by Self-Supervised Models","created":"2024-09-11","cited_by_count":11,"area":"ssm"},{"id":"2505.13930","title":"BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attention","created":"2025-05-20","cited_by_count":10,"area":"ssm"},{"id":"2409.18654","title":"Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models","created":"2024-09-27","cited_by_count":9,"area":"ssm"},{"id":"2410.00070","title":"Mamba for Streaming ASR Combined with Unimodal Aggregation","created":"2024-09-30","cited_by_count":8,"area":"ssm"},{"id":"2408.05057","title":"SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation","created":"2024-08-09","cited_by_count":6,"area":"ssm"},{"id":"2410.09998","title":"SlimSeiz: Efficient Channel-Adaptive Seizure Prediction Using a Mamba-Enhanced Network","created":"2024-10-13","cited_by_count":6,"area":"ssm"},{"id":"2411.07751","title":"SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model","created":"2024-11-12","cited_by_count":6,"area":"ssm"},{"id":"2508.09294","title":"Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative","created":"2025-08-12","cited_by_count":6,"area":"ssm"},{"id":"2409.05034","title":"TF-Mamba: A Time-Frequency Network for Sound Source Localization","created":"2024-09-08","cited_by_count":5,"area":"ssm"},{"id":"2411.06968","title":"Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition","created":"2024-11-11","cited_by_count":5,"area":"ssm"},{"id":"2412.09289","title":"Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices","created":"2024-12-12","cited_by_count":5,"area":"ssm"},{"id":"2502.04593","title":"The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance","created":"2025-02-07","cited_by_count":5,"area":"ssm"},{"id":"2410.06459","title":"Mamba-based Segmentation Model for Speaker Diarization","created":"2024-10-09","cited_by_count":4,"area":"ssm"},{"id":"2409.12413","title":"DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification","created":"2024-09-19","cited_by_count":3,"area":"ssm"},{"id":"2510.03279","title":"MemMamba: Rethinking Memory Patterns in State Space Model","created":"2025-09-28","cited_by_count":3,"area":"ssm"},{"id":"2410.05938","title":"EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment","created":"2024-10-08","cited_by_count":2,"area":"ssm"},{"id":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2410.11062","title":"CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning","created":"2024-10-14","cited_by_count":2,"area":"ssm"},{"id":"2502.01185","title":"Deep Active Speech Cancellation with Mamba-Masking Network","created":"2025-02-03","cited_by_count":2,"area":"ssm"},{"id":"2506.12606","title":"An Exploration of Mamba for Speech Self-Supervised Models","created":"2025-06-14","cited_by_count":2,"area":"ssm"},{"id":"2411.03260","title":"ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removal","created":"2024-11-05","cited_by_count":1,"area":"ssm"},{"id":"2411.06217","title":"Selective State Space Model for Monaural Speech Enhancement","created":"2024-11-09","cited_by_count":1,"area":"ssm"},{"id":"2411.08909","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","created":"2024-10-29","cited_by_count":1,"area":"ssm"},{"id":"2510.18684","title":"MLMA: Towards Multilingual ASR With Mamba-based Architectures","created":"2025-10-21","cited_by_count":1,"area":"ssm"},{"id":"2601.02944","title":"XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection","created":"2026-01-06","cited_by_count":1,"area":"ssm"},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2408.15379","title":"DualKanbaFormer: An Efficient Selective Sparse Framework for Multimodal Aspect-based Sentiment Analysis","created":"2024-08-27","cited_by_count":0,"area":"ssm"},{"id":"2508.07363","title":"Keyword Mamba: Spoken Keyword Spotting with State Space Models","created":"2025-08-10","cited_by_count":0,"area":"ssm"},{"id":"2509.02471","title":"ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous Sound Detection","created":"2025-09-02","cited_by_count":0,"area":"ssm"},{"id":"2509.18691","title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","created":"2025-09-23","cited_by_count":0,"area":"ssm"},{"id":"2509.24020","title":"Hazy Pedestrian Trajectory Prediction via Physical Priors and Graph-Mamba","created":"2025-09-28","cited_by_count":0,"area":"ssm"},{"id":"2512.03563","title":"State Space Models for Bioacoustics: A Comparative Evaluation with Transformers","created":"2025-12-03","cited_by_count":0,"area":"ssm"},{"id":"2604.00292","title":"MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control","created":"2026-03-31","cited_by_count":0,"area":"ssm"},{"id":"2606.15638","title":"MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio","created":"2026-06-14","cited_by_count":0,"area":"ssm"},{"id":"2609.18009","title":"SG-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement","created":"2026-09-16","cited_by_count":0,"area":"ssm"},{"id":"2609.26000","title":"SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr\\\"odinger Bridges","created":"2026-09-22","cited_by_count":0,"area":"ssm"},{"id":"2610.15453","title":"BridgeCodec: Mamba Enhanced Neural Audio Codec with Schr\\\"odinger Bridge at Low Bitrate","created":"2026-10-11","cited_by_count":0,"area":"ssm"}],"next_cursor":null}