← Back to all news
arXiv Computation and Language By Rong Chao, Sung-Feng Huang, Moreno La Quatra, Sabato Marco Siniscalchi, Wen-Huang Cheng, Szu-Wei Fu, Yu Tsao

RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

Read the original on arXiv Computation and Language →

RT-SEMamba is a fully causal speech enhancement model that uses causal time‑frequency Mamba blocks instead of Transformer‑based architectures, allowing efficient long‑form inference with a fixed‑size recurrent state. The authors introduce a progressive knowledge distillation strategy that compresses an 8‑layer teacher into a single‑layer student by jointly distilling spectral outputs and intermediate representations. On the Voicebank‑DEMAND benchmark, the 8‑layer model achieves 3.32 PESQ under a 25 ms latency constraint, while the distilled 1‑layer student improves from 3.06 to 3.18 PESQ, maintains the same steady‑state real‑time factor, and runs 2.64× faster than the teacher.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
6d ago

Acoustic-to-Text KV Compression for Full-Duplex Speech Models

The paper introduces acoustic-to-text KV compression for full‑duplex speech models, converting acoustic key‑value states into compact textual memory during listening‑time slack. When the KV cache exceeds a target budget, older acoustic states are evicted while transcripts and recent acoustic context are retained. Experiments on ten‑minute LongSpeech sessions show a 64.6% reduction in peak streaming KV‑cache size and improved transcription, temporal question answering, and summarization, with comparable pause‑handling, turn‑taking, and interruption performance in Full‑Duplex‑Bench.

By Yejin Lee, Seungbeom Kim, Yongha Lee, Kyuhong Shim
llmsnlpfine-tuningefficiency
More like this →
arXiv AI
2d ago

REALM: Retrospective Encoder Alignment for LFP Modeling

REALM is a retrospective knowledge distillation framework that enables causal decoding of behavior from local field potentials (LFPs). It trains a bidirectional Mamba‑2 teacher on multi‑session data using continuous masked autoencoding, then distills its representations into a compact causal student model. The resulting LFP‑only decoder achieves the highest mean accuracy among compared methods, surpassing state‑of‑the‑art baselines while using fewer parameters and less pretraining time.

By Peicheng Wu, Zhenyu Bu, Runze Ma, Lin Du
fine-tuningefficiencymultimodalbenchmarkssafety
More like this →