Papers › Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech...

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation

14 Oct 2019arXiv:1910.06379archive 2025-07-28

Yi Luo, Zhuo Chen, Takuya Yoshioka

Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods. Unlike the time-frequency domain approaches, the time-domain separation systems often receive input sequences consisting of a huge number of time steps, which introduces challenges for modeling extremely long sequences. Conventional recurrent neural networks (RNNs) are not effective for modeling such long sequences due to optimization difficulties, while one-dimensional convolutional neural networks (1-D CNNs) cannot perform utterance-level sequence modeling when its receptive field is smaller than the sequence length. In this paper, we propose dual-path recurrent neural network (DPRNN), a simple yet effective method for organizing RNN layers in a deep structure to model extremely long sequences. DPRNN splits the long sequential input into smaller chunks and applies intra- and inter-chunk operations iteratively, where the input length can be made proportional to the square root of the original sequence length in each operation. Experiments show that by replacing 1-D CNN with DPRNN and apply sample-level modeling in the time-domain audio separation network (TasNet), a new state-of-the-art performance on WSJ0-2mix is achieved with a 20 times smaller model than the previous best system.

PaperPDFCodeCode Syntology ran

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 22 code samples harvested from 4 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 4 repositories, 19 ran (17 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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.

JusperLee/Dual-Path-RNN-Pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
ZhangYu-x/dprnn_mindspore mentioned on GitHubmindsporeSyntology: not harvested report
fgnt/padertorch mentioned on GitHubpytorchMITSyntology: 12 samples, 9 ran (0 instrument-failed) · 3 unverified report
mpariente/asteroid mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement (arXiv:2008.00264; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 4 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
saurjya/asteroid mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural... (arXiv:2007.13975; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
sp-uhh/dual-path-rnn mentioned on GitHubtfMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
yluo42/TAC mentioned on GitHubpytorchSyntology: not harvested report
lyqcom/dprnn mindsporeApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

22 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 3 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
15ran
3unverified

Licence: 0 of the 22 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 4 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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

JusperLee/Dual-Path-RNN-Pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
make_optimizer in 32 papers train_rnn.py ran · our draft was wrong Apache-2.0 (permissive) · b448dde01277a441 · report fixture: signature params:generator/0/?, opt:dict/0/? · returned Adam · level recorded 2026-09-22
select_norm in 6 papers model/model_rnn.py ran · our draft was wrong Apache-2.0 (permissive) · d7a32d1e19ee3c3c · report fixture: signature norm:str/0/str, dim:int/0/int, shape:int/0/int · returned GlobalLayerNorm · level recorded 2026-09-22
fgnt/padertorch community (archive-listed) 12 samples, 9 ran (0 instrument-failed) · 3 unverified
dataclass_to_config padertorch/configurable.py ran MIT (permissive) · fc587f8fbdac1258 · report fixture: signature cls:callable/0/?, depth:int/0/int, force_valid_config:bool/0/bool · returned dict · level recorded 2026-09-24
import_class in 29 papers padertorch/configurable.py ran MIT (permissive) · 64824c28c3db576f · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-24
normalize_axis in 7 papers padertorch/utils.py ran MIT (permissive) · f947a5b97bfeeae2 · report fixture: signature x:Tensor/3/float, axis:int/0/int · returned tuple · level recorded 2026-09-24
num_parameters in 6 papers padertorch/summary/model_info.py ran MIT (permissive) · 61842f44f2c99c11 · report fixture: signature module:callable/0/? · returned ModelParameterSize · level recorded 2026-09-24
overlap_add padertorch/modules/dual_path_rnn.py ran MIT (permissive) · 5ecc05344e08fef2 · report fixture: signature signal:Tensor/4/float, hop_size:int/0/int, unpad:bool/0/bool · returned Tensor · level recorded 2026-09-24
pack in 10 papers padertorch/modules/dual_path_rnn.py ran MIT (permissive) · 27419265dcbf8198 · report fixture: signature x:Tensor/3/float, sequence_lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-24
to_list in 62 papers padertorch/utils.py ran MIT (permissive) · 9bb35d2d16d87796 · report fixture: signature x:int/0/int, length:NoneType/0/? · returned list · level recorded 2026-09-24
to_numpy in 103 papers
census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
padertorch/utils.py ran MIT (permissive) · 84e8db0cb51a0bbc · report fixture: signature array:Tensor/2/float, detach:bool/0/bool, copy:bool/0/bool · returned ndarray · level recorded 2026-09-24
torch_dataclass padertorch/base.py ran MIT (permissive) · b1f2043a92e934a3 · report fixture: signature cls:callable/0/? · returned type · level recorded 2026-09-24
dumps_config padertorch/io.py unverified MIT (permissive) · bbe5f26fed1e537e · report
fix_doctext_import_class padertorch/configurable.py unverified MIT (permissive) · 4c311e7c82e652b3 · report
load_config in 389 papers padertorch/io.py unverified MIT (permissive) · 77067b06b04d7030 · report
sp-uhh/dual-path-rnn community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
log10 in 5 papers src/loss.py ran MIT (permissive) · 51efffa5a60c50da · report fixture: signature x:SymbolicTensor/1/float · returned SymbolicTensor · level recorded 2026-09-24
permutation_invariant_loss src/loss.py ran MIT (permissive) · 6562d5d49cd2bbfd · report fixture: signature y_true:EagerTensor/3/float, y_pred:EagerTensor/3/float · returned SymbolicTensor · level recorded 2026-09-24
sisnr src/loss.py ran MIT (permissive) · 5fc1af7ade37a222 · report fixture: signature s:EagerTensor/2/float, s_hat:EagerTensor/2/float, do_expand:bool/0/bool, eps:float/0/float · returned SymbolicTensor · level recorded 2026-09-24
text_file_2_list src/utils.py ran MIT (permissive) · bdae77c463a833ba · report fixture: signature text_file:str/0/str · returned list · level recorded 2026-09-24
lyqcom/dprnn community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
cal_SISNR src/evaluate.py ran · violated contract fingerprinted Apache-2.0 (permissive) · faac9c0b7e1a08c5 · 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 src/evaluate.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · b19791aa06bb7b9b · report fixture: signature src_ref:ndarray/2/float, src_est:ndarray/2/float, mix:ndarray/1/float · returned float64 · level recorded 2026-09-22
dynamic_lr in 7 papers src/lr_sch.py ran Apache-2.0 (permissive) · 21022703fec0e252 · report fixture: signature step_per_epoch:int/0/int, epoch:int/0/int · returned list · level recorded 2026-09-24
pad_list in 9 papers src/data_test1.py ran Apache-2.0 (permissive) · 4e2cb218ceb2833d · report fixture: signature xs:list/1/ndarray · returned ndarray · level recorded 2026-09-24

Tasks

Speech Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Separation WSJ0-2mix Dual-path RNN SI-SDRi 18.8 #29 of 40 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

BiLSTMLSTMSigmoid ActivationTanh Activation

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