TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation

arXiv:2606.29575 · cs.SD, cs.AI · Submitted 2026-06-28 · Read on arXiv

cs.SD, cs.AI

Submitted: 2026-06-28

Updated: 2026-09-07

Comments: Accepted to Interspeech 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 9× in this paper · explained in 1 episode
• Mixture of Experts — 5× in this paper · explained in 2 episodes
• Computational overhead — 3× in this paper · explained in 2 episodes
• Edge Deployment — 3× in this paper · explained in 2 episodes
• Mixture-of-Experts (MoE) — 3× in this paper · explained in 7 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Edge Devices — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Predictive Coding — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Short-Time Objective Intelligibility — 1× in this paper
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• The VoicePrivacy 2024 Challenge Evaluation Plan
• TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
• TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids
• Searching for Activation Functions
• Decoupled Weight Decay Regularization
• SGDR: Stochastic Gradient Descent with Warm Restarts
• An efficient encoder-decoder architecture with top-down attention for speech separation

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