SepMamba: State-space models for speaker separation using Mamba
- URL: http://arxiv.org/abs/2410.20997v1
- Date: Mon, 28 Oct 2024 13:20:53 GMT
- Title: SepMamba: State-space models for speaker separation using Mamba
- Authors: Thor Højhus Avenstrup, Boldizsár Elek, István László Mádi, András Bence Schin, Morten Mørup, Bjørn Sand Jensen, Kenny Falkær Olsen,
- Abstract summary: We propose SepMamba, a U-Net-based architecture composed primarily of bidirectional Mamba layers.
We find that our approach outperforms similarly-sized prominent models on the WSJ0 2-speaker dataset.
- Score: 2.840381306234341
- License:
- Abstract: Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense computational demands, precluding their use in many practical applications. As a computationally efficient alternative with similar modeling capabilities, Mamba was recently introduced. We propose SepMamba, a U-Net-based architecture composed primarily of bidirectional Mamba layers. We find that our approach outperforms similarly-sized prominent models - including transformer-based models - on the WSJ0 2-speaker dataset while enjoying a significant reduction in computational cost, memory usage, and forward pass time. We additionally report strong results for causal variants of SepMamba. Our approach provides a computationally favorable alternative to transformer-based architectures for deep speech separation.
Related papers
- MatIR: A Hybrid Mamba-Transformer Image Restoration Model [95.17418386046054]
We propose a Mamba-Transformer hybrid image restoration model called MatIR.
MatIR cross-cycles the blocks of the Transformer layer and the Mamba layer to extract features.
In the Mamba module, we introduce the Image Inpainting State Space (IRSS) module, which traverses along four scan paths.
arXiv Detail & Related papers (2025-01-30T14:55:40Z) - U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation [0.0]
We propose U-mamba-net: a lightweight Mamba-based U-style model for speech separation in complex environments.
Mamba is a state space sequence model that incorporates feature selection capabilities. U-style network is a fully convolutional neural network whose symmetric contracting and expansive paths are able to learn multi-resolution features.
arXiv Detail & Related papers (2024-12-24T06:51:21Z) - Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement [54.427965535613886]
Mamba, as a novel state-space model (SSM), has gained widespread application in natural language processing and computer vision.
In this work, we introduce Mamba-SEUNet, an innovative architecture that integrates Mamba with U-Net for SE tasks.
arXiv Detail & Related papers (2024-12-21T13:43:51Z) - MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs.
We propose the MobileMamba framework, which balances efficiency and performance.
MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
arXiv Detail & Related papers (2024-11-24T18:01:05Z) - ReMamba: Equip Mamba with Effective Long-Sequence Modeling [50.530839868893786]
We propose ReMamba, which enhances Mamba's ability to comprehend long contexts.
ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process.
arXiv Detail & Related papers (2024-08-28T02:47:27Z) - Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models [92.36510016591782]
We present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs)
Our method, called MOHAWK, is able to distill a Mamba-2 variant based on the Phi-1.5 architecture using only 3B tokens and a hybrid version (Hybrid Phi-Mamba) using 5B tokens.
Despite using less than 1% of the training data typically used to train models from scratch, Phi-Mamba boasts substantially stronger performance compared to all past open-source non-Transformer models.
arXiv Detail & Related papers (2024-08-19T17:48:11Z) - How Effective are State Space Models for Machine Translation? [19.509486069758495]
Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts.
Recent works propose to replace attention with linear recurrent layers.
It remains unclear whether these models are competitive with transformers in machine translation.
arXiv Detail & Related papers (2024-07-07T20:21:49Z) - Demystify Mamba in Vision: A Linear Attention Perspective [72.93213667713493]
Mamba is an effective state space model with linear computation complexity.
We show that Mamba shares surprising similarities with linear attention Transformer.
We propose a Mamba-Inspired Linear Attention (MILA) model by incorporating the merits of these two key designs into linear attention.
arXiv Detail & Related papers (2024-05-26T15:31:09Z) - SPMamba: State-space model is all you need in speech separation [20.168153319805665]
CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies.
We introduce an innovative speech separation method called SPMamba.
This model builds upon the robust TF-GridNet architecture, replacing its traditional BLSTM modules with bidirectional Mamba modules.
arXiv Detail & Related papers (2024-04-02T16:04:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.