Papers › ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based...

ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification

14 May 2020arXiv:2005.07143links table onlyarchive 2025-07-28

Brecht Desplanques, Jenthe Thienpondt, Kris Demuynck

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Current speaker verification techniques rely on a neural network to extract speaker representations. The successful x-vector architecture is a Time Delay Neural Network (TDNN) that applies statistics pooling to project variable-length utterances into fixed-length speaker characterizing embeddings. In this paper, we propose multiple enhancements to this architecture based on recent trends in the related fields of face verification and computer vision. Firstly, the initial frame layers can be restructured into 1-dimensional Res2Net modules with impactful skip connections. Similarly to SE-ResNet, we introduce Squeeze-and-Excitation blocks in these modules to explicitly model channel interdependencies. The SE block expands the temporal context of the frame layer by rescaling the channels according to global properties of the recording. Secondly, neural networks are known to learn hierarchical features, with each layer operating on a different level of complexity. To leverage this complementary information, we aggregate and propagate features of different hierarchical levels. Finally, we improve the statistics pooling module with channel-dependent frame attention. This enables the network to focus on different subsets of frames during each of the channel's statistics estimation. The proposed ECAPA-TDNN architecture significantly outperforms state-of-the-art TDNN based systems on the VoxCeleb test sets and the 2019 VoxCeleb Speaker Recognition Challenge.

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 27 code samples harvested from 5 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 0 violated, 24 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 27 samples from 5 repositories, 26 ran (24 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

LKLQQ/ecapa_tdnn mentioned on GitHubmindsporeApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
gzhu06/tdspkr-mismatch-study mentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (1 instrument-failed) · 1 unverified report
joovvhan/ecapa-tdnn mentioned on GitHubpytorchSyntology: not harvested report
magnumresearchgroup/auxiliaryrawnet mentioned on GitHubpytorchSyntology: not harvested report
ol-mega/ppca mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 7 ran (0 instrument-failed) · 0 unverified report
taoruijie/ecapa-tdnn mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
taoruijie/ecapatdnn mentioned on GitHubpytorchMITSyntology: not harvested report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
PunkMale/ECAPA-TDNN-CNCeleb pytorchApache-2.0Syntology: 4 samples, 4 ran (1 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

27 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 0 violated, 24 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
1ran; the contract check could not run
24ran
1unverified

Licence: 1 of the 27 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 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.

LKLQQ/ecapa_tdnn community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
compute_fa_miss src/metrics.py ran Apache-2.0 (permissive) · 8a1f2f7df5f4b6fe · report fixture: signature scores:ndarray/1/float, labels:ndarray/1/int, pos_label:int/0/int, return_thresholds:bool/0/bool · returned tuple · level recorded 2026-09-24
get_EER src/metrics.py ran Apache-2.0 (permissive) · 009c08f278c64a6a · report fixture: signature P_fa:ndarray/1/float, P_miss:ndarray/1/float, thresholds:ndarray/1/float · returned tuple · level recorded 2026-09-24
get_EER_from_scores src/metrics.py ran Apache-2.0 (permissive) · ad04c8794c939048 · report fixture: signature scores:ndarray/1/float, labels:ndarray/1/int, pos_label:int/0/int · returned tuple · level recorded 2026-09-24
gzhu06/tdspkr-mismatch-study community (archive-listed) 11 samples, 10 ran (1 instrument-failed) · 1 unverified
SE_Res2Block backbones/aggregator/ECAPA-TDNN.py ran MIT (permissive) · bb83d95621d7219f · report fixture: signature channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, scale:int/0/int · returned Sequential · level recorded 2026-09-24
calculate_eer in 5 papers evaluate/eer_monitor.py ran fingerprinted MIT (permissive) · 0c85a144d4c6f68a · report fixture: signature positive_sim:list/1/float, negative_sim:list/1/float · returned tuple · level recorded 2026-09-24
cosine_similarity in 120 papers
census: 26 implementations from 30 papers, 11 distinct outputs across 5 buckets, one shared input per bucket
evaluate/eer_monitor.py ran fingerprinted MIT (permissive) · 5bdb987f035ec4ec · report fixture: signature embed1:ndarray/2/float, embed2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
data_catalog preprocessing/wavform_extract.py ran fingerprinted MIT (permissive) · 83e2c902cae568f3 · report fixture: signature dataset_dir:str/0/str, pattern:str/0/str · returned DataFrame · level recorded 2026-09-24
find_files in 21 papers preprocessing/wavform_extract.py ran fingerprinted MIT (permissive) · 9dbd7f6108f96407 · report fixture: signature directory:str/0/str, sample_num:int/0/int, pattern:str/0/str · returned list · level recorded 2026-09-24
get_last_checkpoint_if_any utils.py ran MIT (permissive) · d15bcb24b6237cdb · report fixture: signature checkpoint_folder:str/0/str · returned str · level recorded 2026-09-24
latest_checkpoint_path in 9 papers trainer/train_utils.py ran MIT (permissive) · 1d6005e9f2222eee · report fixture: signature dir_path:str/0/str, regex:str/0/str · returned tuple · level recorded 2026-09-24
natural_sort in 6 papers utils.py ran · our draft was wrong MIT (permissive) · 1677ad306233c7b7 · report fixture: signature l:list/1/str · returned list · level recorded 2026-09-22
pickle2array utils.py ran MIT (permissive) · 69748fb6d2228cc0 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
split_data in 68 papers trainer/train_utils.py ran MIT (permissive) · 92b93a196c3d8b18 · report fixture: signature files:list/1/str, labels:list/1/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
trial_eer evaluate/eer_monitor.py unverified MIT (permissive) · 72855f03c7884551 · report
ol-mega/ppca community (archive-listed) 7 samples, 7 ran (0 instrument-failed) · 0 unverified
get_padding_elem speechbrain/nnet/CNN.py ran Apache-2.0 (permissive) · 8feeecfbeb765eab · report fixture: signature L_in:int/0/int, stride:int/0/int, kernel_size:int/0/int, dilation:int/0/int · returned list · level recorded 2026-09-25
get_padding_elem_transposed speechbrain/nnet/CNN.py ran Apache-2.0 (permissive) · 26b6efc761f6e025 · report fixture: signature L_out:int/0/int, L_in:int/0/int, stride:int/0/int, kernel_size:int/0/int, dilation:int/0/int, output_padding:int/0/int · returned int · level recorded 2026-09-25
pack_padded_sequence speechbrain/nnet/RNN.py ran Apache-2.0 (permissive) · 4d856b195967f759 · report fixture: signature inputs:Tensor/3/float, lengths:Tensor/1/float · returned PackedSequence · level recorded 2026-09-25
pad_packed_sequence speechbrain/nnet/RNN.py ran Apache-2.0 (permissive) · 7c9d9bad06c577fb · report fixture: signature inputs:PackedSequence/1/Tensor · returned Tensor · level recorded 2026-09-25
parse_arguments in 61 papers speechbrain/core.py ran Apache-2.0 (permissive) · bd8ed1453a55a2df · report fixture: signature arg_list:list/1/str · returned tuple · level recorded 2026-09-24
quantize_midrise anonymization_methods/quantize_lpc_poles.py ran Apache-2.0 (permissive) · 298f364b3f304c9f · report fixture: signature x:ndarray/1/float, bits:int/0/int, range_max:int/0/int, range_min:int/0/int · returned ndarray · level recorded 2026-09-24
quantize_midtread anonymization_methods/quantize_lpc_poles.py ran Apache-2.0 (permissive) · 8b5629f75ceda907 · report fixture: signature x:ndarray/1/float, bits:int/0/int, range_max:int/0/int, range_min:int/0/int, limit:bool/0/bool · returned ndarray · level recorded 2026-09-24
taoruijie/ecapa-tdnn community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
init_args in 12 papers tools.py ran MIT (permissive) · 9f9dfffa0e162e11 · report fixture: signature args:Namespace/0/? · returned Namespace · level recorded 2026-09-24
tuneThresholdfromScore tools.py ran MIT (permissive) · e40eb8a3ee8e21ed · report fixture: signature scores:ndarray/1/float, labels:ndarray/1/int, target_fa:list/1/float, target_fr:list/1/float · returned tuple · level recorded 2026-09-24
PunkMale/ECAPA-TDNN-CNCeleb community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
ComputeErrorRates tools.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · 2f8f70723c6fc25c · report fixture: signature scores:list/1/float, labels:list/1/int · returned tuple · level recorded 2026-09-24
findAllUtt dataset.py ran fingerprinted Apache-2.0 (permissive) · 18d1c1af085a8476 · report fixture: signature dirName:str/0/str, extension:str/0/str, speaker_level:int/0/int · returned tuple · level recorded 2026-09-24
init_args in 12 papers tools.py ran Apache-2.0 (permissive) · fcc13d262968ef5f · report fixture: signature args:Args/0/? · returned Args · level recorded 2026-09-24
tuneThresholdfromScore tools.py ran Apache-2.0 (permissive) · 4b2feff2caedf01e · report fixture: signature scores:ndarray/1/float, labels:ndarray/1/int, target_fa:list/1/float, target_fr:list/1/float · returned tuple · level recorded 2026-09-24

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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