BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge

arXiv:2609.28758 · cs.SD, cs.CL · Submitted 2026-09-23 · Read on arXiv

cs.SD, cs.CL

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Embeddings — 10× in this paper · explained in 2 episodes
• Clustering — 8× in this paper · explained in 2 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Pseudo-labels — 5× in this paper · explained in 2 episodes
• Self-Supervised Learning — 5× in this paper · explained in 8 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Representation Learning — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• Transformer — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 1× in this paper
• Redundancy — 1× in this paper · explained in 2 episodes

Sources

• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
• The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• BEATs: Audio Pre-Training with Acoustic Tokenizers
• Root Mean Square Layer Normalization
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Decoupled Weight Decay Regularization
• Robust Speech Recognition via Large-Scale Weak Supervision
• FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment