Papers › Generalized End-to-End Loss for Speaker Verification

Generalized End-to-End Loss for Speaker Verification

28 Oct 2017arXiv:1710.10467archive 2025-07-28

Li Wan, Quan Wang, Alan Papir, Ignacio Lopez Moreno

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that are difficult to verify at each step of the training process. Additionally, the GE2E loss does not require an initial stage of example selection. With these properties, our model with the new loss function decreases speaker verification EER by more than 10%, while reducing the training time by 60% at the same time. We also introduce the MultiReader technique, which allows us to do domain adaptation - training a more accurate model that supports multiple keywords (i.e. "OK Google" and "Hey Google") as well as multiple dialects.

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

No sample from the archive's official repository (google/speaker-id) is linked to this paper; the 27 samples below come from 9 community repositories. Syntology harvested code from google/speaker-id for another paper.

google/speaker-id: Syntology's graph links these samples to DiarizationLM: Speaker Diarization Post-Processing with Large Language Models (arXiv:2401.03506; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 27 code samples harvested from 9 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) · 8 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 9 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 19 samples that ran has no recorded date.

30 repositories listed; official and paper-mentioned ones first.

google/speaker-id officialSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiarizationLM: Speaker Diarization Post-Processing with Large Language Models (arXiv:2401.03506; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Aurora11111/speaker-recognition-pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
Aurora11111/voiceprint mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
CorentinJ/Real-Time-Voice-Cloning mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
HarryVolek/PyTorch_Speaker_Verification mentioned on GitHubpytorchBSD-3-ClauseSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Janghyun1230/Speaker_Verification mentioned on GitHubtfMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
JanhHyun/Speaker_Verification mentioned on GitHubtfMITSyntology: not harvested report
JeffT13/VoiceEncoder mentioned on GitHubpytorchSyntology: not harvested report
JeffT13/rd-diarization mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
Suhee05/Text-Independent-Speaker-Verification mentioned on GitHubtfSyntology: not harvested report
aijianiula0601/ge2eloss-svf mentioned on GitHubtfSyntology: not harvested report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
cvqluu/GE2E-Loss mentioned on GitHubpytorchSyntology: not harvested report
dalonlobo/diarization-experiments mentioned on GitHubtfSyntology: not harvested report
gkv856/speaker_embedding_GE2E_loss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
hanqingguo/GE2E mentioned on GitHubpytorchBSD-3-ClauseSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
icewing1996/baseline mentioned on GitHubpytorchSyntology: not harvested report
luomingshuang/GE2E-SV-TI-Chinese-LMS mentioned on GitHubpytorchBSD-3-ClauseSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
luomingshuang/GE2E-SV-TI-Timit-LMS mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
luomingshuang/GE2E-SV-TI-Voxceleb-LMS mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
luomingshuang/GE2E-SV-TI-thchs30-LMS mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
muskang48/Speaker-Diarization mentioned on GitHubtfSyntology: not harvested report
piotrkawa/audio-deepfake-source-tracing mentioned on GitHubpytorchSyntology: not harvested report
resemble-ai/Resemblyzer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of... (arXiv:2501.03181; that paper's own run record: 1 ran (of which 0 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); nothing checks that they implement this paper's method. report
rf5/simple-speaker-embedding mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tigthor/Voice-Cloning-AI mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yistLin/dvector mentioned on GitHubpytorchSyntology: not harvested report
yui-mhcp/base_dl_project mentioned on GitHubtfAGPL-3.0Syntology: not harvested report
zhangmin4215/PyTorch_Speaker_Verification mentioned on GitHubpytorchBSD-3-ClauseSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified 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

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: 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) · 8 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
1ran · our draft was wrong
1ran; the contract check could not run
15ran
8unverified

Licence: 2 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, 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 9 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.

Aurora11111/speaker-recognition-pytorch community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
merge_dict in 13 papers hparam.py ran BSD-3-Clause (permissive) · 0cfe2baee7e49f75 · report fixture: signature user:dict/0/?, default:dict/0/? · returned dict · level recorded 2026-09-25
batch_cosine_similarity triplet_loss.py unverified BSD-3-Clause (permissive) · 89800dcb89ac9137 · report
deep_speaker_loss triplet_loss.py unverified BSD-3-Clause (permissive) · 30c3a463de241489 · report
getdata data.py unverified BSD-3-Clause (permissive) · b19223789c3048c4 · report
load_hparam hparam.py unverified BSD-3-Clause (permissive) · 946edc002ef7c1b6 · report
HarryVolek/PyTorch_Speaker_Verification community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_centroid utils.py ran BSD-3-Clause (permissive) · 0709e60b0d9e8ae5 · report fixture: signature embeddings:list/1/list, speaker_num:int/0/int, utterance_num:int/0/int · returned Tensor · level recorded 2026-09-25
get_centroids in 8 papers utils.py ran fingerprinted BSD-3-Clause (permissive) · 5c03130d658096c8 · report fixture: signature embeddings:Tensor/3/float · returned Tensor · level recorded 2026-09-25
get_centroids_prior utils.py ran BSD-3-Clause (permissive) · 06be3bf4f63f2b74 · report fixture: signature embeddings:list/1/list · returned Tensor · level recorded 2026-09-25
Janghyun1230/Speaker_Verification community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
str2bool in 533 papers configuration.py ran · violated contract MIT (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
JeffT13/rd-diarization community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
Diarize RDSV/rdsv.py ran Apache-2.0 (permissive) · 31b96b748f3b2650 · report fixture: signature ral:RAL_Container/0/?, cont_embeds:ndarray/2/float, embed_times:list/1/list, sim_thresh:float/0/float, score_thresh:float/0/float, min_seg:int/0/int · returned list · level recorded 2026-09-26
getAudio SCOTUS/mp3_curl_commands.py ran Apache-2.0 (permissive) · 527bd051353c260e · report fixture: signature transcripts:list/1/dict · returned list · level recorded 2026-09-26
getMeta SCOTUS/make_transcripts.py ran Apache-2.0 (permissive) · a3894bb8fc3101e3 · report fixture: signature docket:str/0/str, data:dict/0/? · returned tuple · level recorded 2026-09-26
logit_thresh RDSV/run_LR.py ran Apache-2.0 (permissive) · f148b7b019bd0110 · report fixture: signature log:list/1/ndarray, l:float/0/float · returned list · level recorded 2026-09-26
get_case SCOTUS/mp3_curl_commands.py unverified Apache-2.0 (permissive) · bdd6ae5c8ffd396e · report
get_http_json SCOTUS/mp3_curl_commands.py unverified Apache-2.0 (permissive) · 61045b44f5159adc · report
gkv856/speaker_embedding_GE2E_loss community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_pre_trained_embedding_model embedding_model_GE2E/s2_model_GE2E_loss_speach_embed.py ran · our draft was wrong no licence file found · pointer only · 853ff1d60d8fe25d · report fixture: signature hp:HPConfig/0/?, use_path_as_absolute:bool/0/bool · returned ModelGE2ELossSpeachEmbed · level recorded 2026-09-22
hanqingguo/GE2E community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_centroids in 8 papers utils.py ran BSD-3-Clause (permissive) · b21b997a285edb93 · report fixture: signature embeddings:list/1/list · returned Tensor · level recorded 2026-09-26
get_cossim utils.py ran fingerprinted BSD-3-Clause (permissive) · bd0b923fc30cfbab · report fixture: signature embeddings:Tensor/3/float, centroids:Tensor/2/float · returned Tensor · level recorded 2026-09-26
luomingshuang/GE2E-SV-TI-Chinese-LMS community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
read_wave vad.py ran BSD-3-Clause (permissive) · aa4702b2823edf0c · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-26
luomingshuang/GE2E-SV-TI-Timit-LMS community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
align_embeddings dvector_create.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant BSD-3-Clause (permissive) · d628e47b97ec4d2d · report fixture: signature embeddings:ndarray/2/float · returned ndarray · level recorded 2026-09-22
concat_segs dvector_create.py ran · honoured contract BSD-3-Clause (permissive) · fa3887e58fe3d162 · report fixture: signature times:list/1/tuple, segs:list/1/ndarray · returned list · level recorded 2026-09-22
zhangmin4215/PyTorch_Speaker_Verification community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
regularization_loss in 8 papers uis-rnn/uisrnn/loss_func.py ran BSD-3-Clause (permissive) · 23bad4461ca9d747 · report fixture: signature params:list/1/Tensor, weight:float/0/float · returned Tensor · level recorded 2026-09-24
sigma2_prior_loss uis-rnn/uisrnn/loss_func.py ran BSD-3-Clause (permissive) · cd29a997e2d51ed2 · report fixture: signature num_non_zero:int/0/int, sigma_alpha:float/0/float, sigma_beta:float/0/float, sigma2:Tensor/1/float · returned Tensor · level recorded 2026-09-24
str2bool in 533 papers uis-rnn/uisrnn/arguments.py ran BSD-3-Clause (permissive) · c6ef3c918426ce63 · report fixture: signature value:str/0/str · returned bool · level recorded 2026-09-26
weighted_mse_loss in 14 papers uis-rnn/uisrnn/loss_func.py ran fingerprinted BSD-3-Clause (permissive) · 720fd03354ee7041 · report fixture: signature input_tensor:Tensor/2/float, target_tensor:Tensor/2/float, weight:Tensor/1/float · returned Tensor · level recorded 2026-09-24
read_wave webrtcvad/example.py unverified BSD-3-Clause (permissive) here; the stored copy is pointer only · 2c4ba80fd768dc88 · report

Tasks

Domain AdaptationSpeaker Verification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speaker Verification CALLHOME GE2E Cosine EER 3.55 #1 of 2 Archive leaderboard report
Speaker Verification CALLHOME Cosine EER 2.38 #2 of 2 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.

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