SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.02063 · 2024

SPMamba: State-space model is all you need in speech separation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2404.02063.json · badge: /api/ran/2404.02063.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jusperlee/spmamba canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
check_parameters Ran
ran, honoured the contract we drafted
jusperlee/spmamba/cal_flops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from JusperLee/Conv-TasNet, is pointer only (licence: NONE) · get_code("bbd39ee3588090e3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from JusperLee/Conv-TasNet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

flops_selective_scan_fn Ran
ran, honoured the contract we drafted
jusperlee/spmamba/cal_flops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from chishengchen/resvmamba, is pointer only (licence: NONE) · get_code("9349a926c58456ec")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from chishengchen/resvmamba, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_tensor_wav Ran
ran; our contract draft was wrong, not the code
jusperlee/spmamba/look2hear/datas/echo2mix_datamodule.py
code served (permissive licence) · get_code("971fc60507ed355e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a small audio waveform tensor
# Shape: (batch_size=2, num_samples=4)
wav_tensor = torch.randn(2, 4)

# eps parameter - small value to avoid division by zero
eps = 1e-08

# std parameter - can be None (will be computed) or a precomputed std tensor
std = None

ARGS = {
    "wav_tensor": wav_tensor,
    "eps": eps,
    "std": std,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
flops_selective_scan_fn 4 other papers
4 dated earlier
2401.10166 (2024-01)
VMamba: Visual State Space Model
2402.15761 (2024-02)
Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning
2403.09338 (2024-03)
LocalMamba: Visual State Space Model with Windowed Selective Scan
and 1 more not named here
check_parameters 2 other papers
2 dated earlier
1809.07454 (2018-09)
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
2002.08688 (2020-02)
An empirical study of Conv-TasNet
normalize_tensor_wav 1 other paper
1 dated earlier
1811.01531 (2018-11)
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies. Although LSTM and Transformer-based speech separation models can avoid this problem, their high complexity makes them face the challenge of computational resources and inference efficiency when dealing with long audio. To address this challenge, 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. These modules effectively model the spatiotemporal relationships between the time and frequency dimensions, allowing SPMamba to capture long-range dependencies with linear computational complexity. Specifically, the bidirectional processing within the Mamba modules enables the model to utilize both past and future contextual information, thereby enhancing separation performance. Extensive experiments conducted on public datasets, including WSJ0-2Mix, WHAM!, and Libri2Mix, as well as the newly constructed Echo2Mix dataset, demonstrated that SPMamba significantly outperformed existing state-of-the-art models, achieving superior results while also reducing computational complexity. These findings highlighted the effectiveness of SPMamba in tackling the intricate challenges of speech separation in complex environments.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.02063")
get_code_for_paper("2404.02063")
have("2404.02063")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.02063.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.02063.svg)](https://syntology.ai/paper/2404.02063)

Connect an agent — have() is free.