paper-with-me

홈 › Papers

MC-SEMamba: A Simple Multi-channel Extension of SEMamba

2024-09-26 · Wen-Yuan Ting, Wenze Ren, Rong Chao, Hsin-Yi Lin, Yu Tsao, Fan-Gang Zeng

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential alternative to transformer-based models because of its efficient modeling of long sequences. In particular, models like SEMamba have demonstrated the effectiveness of the Mamba architecture in single-channel speech enhancement. This paper aims to adapt SEMamba for multi-channel applications with only a small increase in parameters. The resulting system, MC-SEMamba, achieved results on the CHiME3 dataset that were comparable or even superior to several previous baseline models. Additionally, we found that increasing the number of microphones from 1 to 6 improved the speech enhancement performance of MC-SEMamba.

📄 PDF Abstract BibTeX arXiv:2409.17898

Code (0)

등록된 구현이 없습니다.

Tasks

MambaSpeech Enhancement

Methods 이 논문이 사용한 방법론

Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

An Investigation of Incorporating Mamba for Speech Enhancement

2024-05-10 · Rong Chao, Wen-Huang Cheng, Moreno La Quatra, Sabato Marco Siniscalchi 외

This work aims to study a scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. We exploit a Mamba-based regression model to characterize speech signals and build an SE system upon Mamba, termed …

MambaSpeech Enhancement

SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning

2025-03-03 · Luyi Qiu, Tristan Till, Xiaobao Guo, Adams Wai-Kin Kong

Scribble annotations significantly reduce the cost and labor required for dense labeling in large medical datasets with complex anatomical structures. However, current scribble-supervised learning methods are limited in …

DecoderImage SegmentationMambaMedical Image Segmentation+1

PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model

2024-08-07 · Yunlong Huang, Junshuo Liu, Ke Xian, Robert Caiming Qiu

Transformers have significantly advanced the field of 3D human pose estimation (HPE). However, existing transformer-based methods primarily use self-attention mechanisms for spatio-temporal modeling, leading to a quadrat…

3D Human Pose EstimationLong-range modelingMambaMonocular 3D Human Pose Estimation+1

Multi-modal Speech Enhancement with Limited Electromyography Channels

2025-01-11 · Fuyuan Feng, Longting Xu, Rohan Kumar Das

Speech enhancement (SE) aims to improve the clarity, intelligibility, and quality of speech signals for various speech enabled applications. However, air-conducted (AC) speech is highly susceptible to ambient noise, part…

Electromyography (EMG)Speech Enhancement

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

2024-02-26 · wei he, Kai Han, Yehui Tang, Chengcheng Wang 외

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational…

MambaState Space Models