{"total":26,"rows":[{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350,"area":"ssm"},{"id":"2403.09471","title":"MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models","created":"2024-03-14","cited_by_count":46,"area":"ssm"},{"id":"2405.11831","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","created":"2024-05-20","cited_by_count":37,"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":"2406.02178","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","created":"2024-06-04","cited_by_count":19,"area":"ssm"},{"id":"2409.09337","title":"Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution","created":"2024-09-14","cited_by_count":9,"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":"2502.11123","title":"DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities","created":"2025-02-16","cited_by_count":5,"area":"ssm"},{"id":"2309.08551","title":"Augmenting conformers with structured state-space sequence models for online speech recognition","created":"2023-09-15","cited_by_count":3,"area":"ssm"},{"id":"2408.01627","title":"JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model","created":"2024-08-03","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":"2410.06846","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":"2506.12606","title":"An Exploration of Mamba for Speech Self-Supervised Models","created":"2025-06-14","cited_by_count":2,"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":"2506.01138","title":"PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition","created":"2025-06-01","cited_by_count":0,"area":"ssm"},{"id":"2506.02258","title":"Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?","created":"2025-06-02","cited_by_count":0,"area":"ssm"},{"id":"2506.19315","title":"JCAPT: A Joint Modeling Approach for CAPT","created":"2025-06-24","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":"2511.14969","title":"Quality-Controlled Multimodal Emotion Recognition in Conversations with Identity-Based Transfer Learning and MAMBA Fusion","created":"2025-11-18","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":"2603.18031","title":"InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model","created":"2026-03-08","cited_by_count":0,"area":"ssm"},{"id":"2603.21316","title":"HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit","created":"2026-03-22","cited_by_count":0,"area":"ssm"},{"id":"2604.18580","title":"Sessa: Selective State Space Attention","created":"2026-04-20","cited_by_count":0,"area":"ssm"},{"id":"2607.04498","title":"UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization","created":"2026-07-05","cited_by_count":0,"area":"ssm"},{"id":"2607.26751","title":"Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text","created":"2026-07-29","cited_by_count":0,"area":"ssm"},{"id":"2609.28758","title":"BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge","created":"2026-09-23","cited_by_count":0,"area":"ssm"}],"next_cursor":null}