{"total":62,"rows":[{"id":"2405.12609","title":"Mamba in Speech: Towards an Alternative to Self-Attention","created":"2024-05-21","cited_by_count":60,"area":"ssm"},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"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":"2412.16626","title":"Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement","created":"2024-12-21","cited_by_count":10,"area":"ssm"},{"id":"2505.21198","title":"Universal Speech Enhancement with Regression and Generative Mamba","created":"2025-05-27","cited_by_count":7,"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":"2506.02908","title":"Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency","created":"2025-06-03","cited_by_count":6,"area":"diffusion"},{"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":"2409.18828","title":"MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removal","created":"2024-09-27","cited_by_count":5,"area":null},{"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":"2501.06146","title":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","created":"2025-01-10","cited_by_count":4,"area":"ssm"},{"id":"2507.11925","title":"Schr\\\"odinger Bridge Consistency Trajectory Models for Speech Enhancement","created":"2025-07-16","cited_by_count":4,"area":"diffusion"},{"id":"2512.19442","title":"Real-Time Streamable Generative Speech Restoration with Flow Matching","created":"2025-12-22","cited_by_count":4,"area":"diffusion"},{"id":"2506.16231","title":"EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training","created":"2025-06-19","cited_by_count":3,"area":"ssm"},{"id":"2510.16834","title":"Schr\\\"odinger Bridge Mamba for One-Step Speech Enhancement","created":"2025-10-19","cited_by_count":3,"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":"2411.18902","title":"MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2412.04861","title":"MSECG: Incorporating Mamba for Robust and Efficient ECG Super-Resolution","created":"2024-12-06","cited_by_count":2,"area":"ssm"},{"id":"2501.13230","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2502.01185","title":"Deep Active Speech Cancellation with Mamba-Masking Network","created":"2025-02-03","cited_by_count":2,"area":"ssm"},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2506.12606","title":"An Exploration of Mamba for Speech Self-Supervised Models","created":"2025-06-14","cited_by_count":2,"area":"ssm"},{"id":"2507.00966","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","created":"2025-07-01","cited_by_count":2,"area":"ssm"},{"id":"2507.02791","title":"Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2509.19495","title":"ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancement","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2510.18744","title":"Diffusion Buffer for Online Generative Speech Enhancement","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2601.12345","title":"Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios","created":"2026-01-18","cited_by_count":2,"area":null},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2409.10376","title":"Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement","created":"2024-09-16","cited_by_count":1,"area":"ssm"},{"id":"2508.03047","title":"TF-MLPNet: Tiny Real-Time Neural Speech Separation","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2510.18684","title":"MLMA: Towards Multilingual ASR With Mamba-based Architectures","created":"2025-10-21","cited_by_count":1,"area":"ssm"},{"id":"2511.11686","title":"Regularized Schr\\\"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2511.17647","title":"MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence","created":"2025-11-20","cited_by_count":1,"area":"diffusion"},{"id":"2603.23723","title":"Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.24920","title":"Quaternion Self-Attention with Shared Scores","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2409.03377","title":"aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2409.09642","title":"Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement","created":"2024-09-15","cited_by_count":0,"area":"diffusion"},{"id":"2505.16911","title":"Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.07363","title":"Keyword Mamba: Spoken Keyword Spotting with State Space Models","created":"2025-08-10","cited_by_count":0,"area":"ssm"},{"id":"2508.13624","title":"Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement","created":"2025-08-19","cited_by_count":0,"area":"ssm"},{"id":"2508.14556","title":"Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.08470","title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","created":"2025-09-10","cited_by_count":0,"area":"moe"},{"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":"2510.01958","title":"Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement","created":"2025-10-02","cited_by_count":0,"area":"ssm"},{"id":"2510.11058","title":"Robust Photoplethysmography Signal Denoising via Mamba Networks","created":"2025-10-13","cited_by_count":0,"area":"ssm"},{"id":"2511.01868","title":"Condition-Invariant fMRI Decoding of Speech Intelligibility with Deep State Space Model","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.06288","title":"ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2602.04307","title":"Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.12246","title":"TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants","created":"2026-04-14","cited_by_count":0,"area":"ssm"},{"id":"2605.06189","title":"Predictive-Generative Drift Decomposition for Speech Enhancement and Separation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.12662","title":"BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.18611","title":"QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.12099","title":"RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation","created":"2026-08-12","cited_by_count":0,"area":"ssm"},{"id":"2608.12715","title":"HybridSB-MoE: Dual-Domain Schr\\\"odinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement","created":"2026-08-13","cited_by_count":0,"area":"moe"},{"id":"2608.30329","title":"Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.03414","title":"StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios","created":"2026-09-03","cited_by_count":0,"area":null},{"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":"2609.24651","title":"Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.35054","title":"Perceptual Quality Loss or Loss of Perceptual Quality?","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}