{"total":18,"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":"2406.02178","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","created":"2024-06-04","cited_by_count":19,"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":"2410.06459","title":"Mamba-based Segmentation Model for Speaker Diarization","created":"2024-10-09","cited_by_count":4,"area":"ssm"},{"id":"2409.05243","title":"Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations","created":"2024-09-08","cited_by_count":3,"area":"ssm"},{"id":"2408.00370","title":"DiM-Gesture: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2 framework","created":"2024-08-01","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":"2411.14100","title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","created":"2024-11-21","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":"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":"2507.05729","title":"Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners","created":"2025-07-08","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":"2510.04738","title":"Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba","created":"2025-10-06","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":"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"},{"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}