Papers › Voice Separation with an Unknown Number of Multiple Speakers

Voice Separation with an Unknown Number of Multiple Speakers

29 Feb 2020ICML 2020 1arXiv:2003.01531archive 2025-07-28

Eliya Nachmani, Yossi Adi, Lior Wolf

We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 3 repositories linked to this paper: 12 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 12 samples from 2 repositories, 11 ran (9 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/svoice officialmentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Mack189/gdprnn mentioned on GitHubmindsporeApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
muhammad-ahmed-ghani/svoice_demo mentioned on GitHubpytorchSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
enk100/speaker_separation Syntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 12 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
8ran
1unverified

Licence: 9 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

facebookresearch/svoice official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MulCatBlock svoice/models/swave.py ran · metamorphic tier: deterministic licence not identified · pointer only · 92748185c4ff9d16 · report fixture: returned MulCatBlock · level recorded 2026-09-22
Mack189/gdprnn community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
cal_SISNR evaluate.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 891e417fc38edeb0 · report fixture: signature ref_sig:ndarray/1/float, out_sig:ndarray/1/float, eps:float/0/float · returned float64 · level recorded 2026-09-22
cal_SISNRi in 5 papers evaluate.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ca6c3339d98f2a2c · report fixture: signature src_ref:ndarray/2/float, src_est:ndarray/2/float, mix:ndarray/1/float · returned float64 · level recorded 2026-09-22
capture_init src/models/swave.py ran Apache-2.0 (permissive) · ecdad0e168981f5d · report fixture: signature init:callable/0/? · returned function · level recorded 2026-09-24
pad_list in 9 papers preprocess.py ran Apache-2.0 (permissive) · 1e3f6a2103e513ce · report fixture: signature xs:list/1/ndarray · returned ndarray · level recorded 2026-09-24
muhammad-ahmed-ghani/svoice_demo community (archive-listed) 8 samples, 7 ran (2 instrument-failed) · 1 unverified
ByPass svoice/models/swave.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 173650e5ae028b2f · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
DPMulCat svoice/models/swave.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 3b1d338215096fe7 · report fixture: returned DPMulCat · level recorded 2026-09-22
Decoder in 210 papers svoice/models/swave.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 5f72b86aea22a846 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers svoice/models/swave.py ran · metamorphic tier: deterministic fingerprinted licence not identified · pointer only · 820a2cedf7915ddd · report fixture: returned Encoder · level recorded 2026-09-22
Separator svoice/models/swave.py ran · metamorphic tier: deterministic licence not identified · pointer only · facca3bf4fbfc471 · report fixture: returned Separator · level recorded 2026-09-22
capture_init svoice/models/swave.py ran · our draft was wrong licence not identified · pointer only · ccacfa5207d7243d · report fixture: signature init:callable/0/? · returned function · level recorded 2026-09-22
overlap_and_add in 8 papers svoice/models/swave.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 9c926905c0e7a1c7 · report fixture: signature signal:Tensor/3/float, frame_step:int/0/int · returned Tensor · level recorded 2026-09-22
SWave svoice/models/swave.py unverified licence not identified · pointer only · 8967a79d23072fba · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for gated neural networks (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for gated neural networks (graph method: gated neural networks). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. MulCatBlock entry · level 1 · ran · 92748185c4ff9d16

harvested Assembly for gated neural networks (graph method: gated neural networks). 9 bricks; individually on a fixture: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SWave entry · level 0 · unverified · 8967a79d23072fba
  2. Decoder model · level 1 · ran · 5f72b86aea22a846
  3. Encoder model · level 1 · ran · 820a2cedf7915ddd
  4. Separator model · level 1 · ran · facca3bf4fbfc471
  5. capture_init helper · level 1 · ran · our draft was wrong · ccacfa5207d7243d
  6. overlap_and_add helper · level 1 · ran · our draft was wrong · 9c926905c0e7a1c7
  7. DPMulCat model · level 1 · ran · 3b1d338215096fe7
  8. ByPass helper · level 1 · ran · 173650e5ae028b2f
  9. MulCatBlock model · level 1 · ran · 92748185c4ff9d16

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2003.01531") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Speech Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Separation WHAMR! VSUNOS SI-SDRi 12.2 #12 of 18 Archive leaderboard report
Speech Separation WSJ0-2mix Gated DualPathRNN SI-SDRi 20.12 #25 of 40 Archive leaderboard report
Speech Separation WSJ0-3mix Gated DualPathRNN SI-SDRi 16.85 #9 of 9 Archive leaderboard report
Speech Separation WSJ0-4mix Gated DualPathRNN SI-SDRi 12.88 #2 of 5 Archive leaderboard report
Speech Separation WSJ0-5mix Gated DualPathRNN SI-SDRi 10.56 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ConvolutionLSTMPReLUReLUuPIT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections