Papers › Deep Speaker: an End-to-End Neural Speaker Embedding System

Deep Speaker: an End-to-End Neural Speaker Embedding System

5 May 2017arXiv:1705.02304archive 2025-07-28

Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, Zhenyao Zhu

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset. We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.

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="1705.02304")

Code

Syntology Ran 7 of 9 code samples harvested from 4 repositories linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 7 samples from 4 repositories, 5 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

15 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
MainRo/deep-speaker mentioned on GitHubMIT report
Siomarry/Audio_recognition_ mentioned on GitHub report
Siomarry/Siomarry mentioned on GitHub report
andabi/voice-vector mentioned on GitHubtf report
dodoproptit99/deep-speaker mentioned on GitHub report
philipperemy/deep-speaker mentioned on GitHubtf report
prajual/Deep_Speaker mentioned on GitHub report
qqueing/DeepSpeaker-pytorch mentioned on GitHubpytorch report
vohoaiviet/voice-vector mentioned on GitHubtf 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

9 samples harvested; 7 ran; 2 honoured the contract we drafted; 2 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.

2ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 5 of the 9 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; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

calculate_roc qqueing/DeepSpeaker-pytorch/eval_metrics.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 625877b8d181dc24 · report
get prajual/Deep_Speaker/models.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 2cbf4ce7e0235a0d · report
getwavPathAndwavLabel wangleiai/dVectorSpeakerRecognition/kersaSoftmax/dnnTrain.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · cbc4d3a4f90e8027 · report
getwavPathAndwavLabel wangleiai/dVectorSpeakerRecognition/kersaSoftmax/gruTrain.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 9e35c18ce8eaf604 · report
normalize_scores Walleclipse/Deep_Speaker-speaker_recognition_system/test_model.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 6a6418cda28d6455 · report
create_optimizer qqueing/DeepSpeaker-pytorch/train_triplet.py community (archive-listed) unverified MIT (permissive) · d74d2593f3b8926c · report
evaluate qqueing/DeepSpeaker-pytorch/eval_metrics.py community (archive-listed) unverified MIT (permissive) · 1283b5c46e6830d4 · report
calculate_accuracy identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · f975336b5d5f1a80 · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · fac5364e2f53c6db · report

Tasks

ClusteringSpeaker IdentificationSpeaker Recognition

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GRU

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