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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1710.10467")

Code

Syntology Ran 4 of 27 code samples harvested from 9 repositories linked to this paper; 23 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 27 samples from 9 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

Aurora11111/speaker-recognition-pytorch mentioned on GitHubpytorchBSD-3-Clause report
Aurora11111/voiceprint mentioned on GitHubpytorchBSD-3-Clause report
CorentinJ/Real-Time-Voice-Cloning mentioned on GitHubtfNOASSERTION report
HarryVolek/PyTorch_Speaker_Verification mentioned on GitHubpytorchBSD-3-Clause report
Janghyun1230/Speaker_Verification mentioned on GitHubtfMIT report
JanhHyun/Speaker_Verification mentioned on GitHubtfMIT report
JeffT13/VoiceEncoder mentioned on GitHubpytorch report
JeffT13/rd-diarization mentioned on GitHubpytorchApache-2.0 report
aijianiula0601/ge2eloss-svf mentioned on GitHubtf report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0 report
cvqluu/GE2E-Loss mentioned on GitHubpytorch report
gkv856/speaker_embedding_GE2E_loss mentioned on GitHubpytorch report
hanqingguo/GE2E mentioned on GitHubpytorchBSD-3-Clause report
icewing1996/baseline mentioned on GitHubpytorch report
luomingshuang/GE2E-SV-TI-Chinese-LMS mentioned on GitHubpytorchBSD-3-Clause report
luomingshuang/GE2E-SV-TI-Timit-LMS mentioned on GitHubpytorch report
luomingshuang/GE2E-SV-TI-Voxceleb-LMS mentioned on GitHubpytorchBSD-3-Clause report
luomingshuang/GE2E-SV-TI-thchs30-LMS mentioned on GitHubpytorchBSD-3-Clause report
muskang48/Speaker-Diarization mentioned on GitHubtf report
piotrkawa/audio-deepfake-source-tracing mentioned on GitHubpytorch report
resemble-ai/Resemblyzer mentioned on GitHubpytorch report
rf5/simple-speaker-embedding mentioned on GitHubpytorchNOASSERTION report
tigthor/Voice-Cloning-AI mentioned on GitHubpytorchNOASSERTION report
yistLin/dvector mentioned on GitHubpytorch report
yui-mhcp/base_dl_project mentioned on GitHubtfAGPL-3.0 report
zhangmin4215/PyTorch_Speaker_Verification mentioned on GitHubpytorchBSD-3-Clause 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

27 samples harvested; 4 ran; 1 honoured the contract we drafted; 23 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
1ran · fixture could not drive it
23unverified

Licence: 1 of the 27 samples is 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 9 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

align_embeddings luomingshuang/GE2E-SV-TI-Timit-LMS/dvector_create.py community (archive-listed) ran · fixture could not drive it BSD-3-Clause (permissive) · d628e47b97ec4d2d · report
concat_segs luomingshuang/GE2E-SV-TI-Timit-LMS/dvector_create.py community (archive-listed) ran · honoured contract BSD-3-Clause (permissive) · fa3887e58fe3d162 · report
get_pre_trained_embedding_model gkv856/speaker_embedding_GE2E_loss/embedding_model_GE2E/s2_model_GE2E_loss_speach_embed.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 853ff1d60d8fe25d · report
str2bool Janghyun1230/Speaker_Verification/configuration.py community (archive-listed) ran · violated contract MIT (permissive) · f017532fc389cbfe · report
Diarize JeffT13/rd-diarization/RDSV/rdsv.py community (archive-listed) unverified Apache-2.0 (permissive) · 31b96b748f3b2650 · report
batch_cosine_similarity Aurora11111/speaker-recognition-pytorch/triplet_loss.py community (archive-listed) unverified BSD-3-Clause (permissive) · 89800dcb89ac9137 · report
deep_speaker_loss Aurora11111/speaker-recognition-pytorch/triplet_loss.py community (archive-listed) unverified BSD-3-Clause (permissive) · 30c3a463de241489 · report
getAudio JeffT13/rd-diarization/SCOTUS/mp3_curl_commands.py community (archive-listed) unverified Apache-2.0 (permissive) · 527bd051353c260e · report
getMeta JeffT13/rd-diarization/SCOTUS/make_transcripts.py community (archive-listed) unverified Apache-2.0 (permissive) · a3894bb8fc3101e3 · report
get_case JeffT13/rd-diarization/SCOTUS/mp3_curl_commands.py community (archive-listed) unverified Apache-2.0 (permissive) · bdd6ae5c8ffd396e · report
get_centroid HarryVolek/PyTorch_Speaker_Verification/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 0709e60b0d9e8ae5 · report
get_centroids HarryVolek/PyTorch_Speaker_Verification/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 5c03130d658096c8 · report
get_centroids hanqingguo/GE2E/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · b21b997a285edb93 · report
get_centroids_prior HarryVolek/PyTorch_Speaker_Verification/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 06be3bf4f63f2b74 · report
get_cossim hanqingguo/GE2E/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · bd0b923fc30cfbab · report
get_http_json JeffT13/rd-diarization/SCOTUS/mp3_curl_commands.py community (archive-listed) unverified Apache-2.0 (permissive) · 61045b44f5159adc · report
getdata Aurora11111/speaker-recognition-pytorch/data.py community (archive-listed) unverified BSD-3-Clause (permissive) · b19223789c3048c4 · report
load_hparam Aurora11111/speaker-recognition-pytorch/hparam.py community (archive-listed) unverified BSD-3-Clause (permissive) · 946edc002ef7c1b6 · report
logit_thresh JeffT13/rd-diarization/RDSV/run_LR.py community (archive-listed) unverified Apache-2.0 (permissive) · f148b7b019bd0110 · report
merge_dict Aurora11111/speaker-recognition-pytorch/hparam.py community (archive-listed) unverified BSD-3-Clause (permissive) · 0cfe2baee7e49f75 · report
normalize Janghyun1230/Speaker_Verification/utils.py community (archive-listed) unverified MIT (permissive) · fb1e5bf517bebed1 · report
read_wave zhangmin4215/PyTorch_Speaker_Verification/webrtcvad/example.py community (archive-listed) unverified BSD-3-Clause (permissive) · 2c4ba80fd768dc88 · report
read_wave luomingshuang/GE2E-SV-TI-Chinese-LMS/vad.py community (archive-listed) unverified BSD-3-Clause (permissive) · aa4702b2823edf0c · report
regularization_loss zhangmin4215/PyTorch_Speaker_Verification/uis-rnn/uisrnn/loss_func.py community (archive-listed) unverified BSD-3-Clause (permissive) · 23bad4461ca9d747 · report
sigma2_prior_loss zhangmin4215/PyTorch_Speaker_Verification/uis-rnn/uisrnn/loss_func.py community (archive-listed) unverified BSD-3-Clause (permissive) · cd29a997e2d51ed2 · report
str2bool zhangmin4215/PyTorch_Speaker_Verification/uis-rnn/uisrnn/arguments.py community (archive-listed) unverified BSD-3-Clause (permissive) · c6ef3c918426ce63 · report
weighted_mse_loss zhangmin4215/PyTorch_Speaker_Verification/uis-rnn/uisrnn/loss_func.py community (archive-listed) unverified BSD-3-Clause (permissive) · 720fd03354ee7041 · 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