SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1705.02304 · 2017

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

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1705.02304.json · badge: /api/ran/1705.02304.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
wangleiai/dVectorSpeakerRecognition reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
qqueing/DeepSpeaker-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
prajual/Deep_Speaker reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
Walleclipse/Deep_Speaker-speaker_recognition_system reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_accuracy Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from zrui94/insight_mx
pointer only; the stored copy get_code serves, from zrui94/insight_mx, is pointer only (licence: NONE) · get_code("f975336b5d5f1a80")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_roc Ran
ran, honoured the contract we drafted
qqueing/DeepSpeaker-pytorch/eval_metrics.py
code served (permissive licence) · get_code("625877b8d181dc24")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

np.random.seed(42)

# Create sample data for face verification task
# distances: array of distances between face pairs (smaller = more similar)
# labels: boolean array indicating if pairs are actually the same person
# thresholds: array of threshold values to test

n_pairs = 10
n_thresholds = 5

# Generate distances between 0 and 2
distances = np.random.uniform(0, 2, size=n_pairs)

# Generate labels (True if same person, False if different)
labels = np.random.choice([True, False], size=n_pairs)

# Generate thresholds to test (typically range from min to max distance)
thresholds = np.linspace(0, 2, n_thresholds)

ARGS = {
    'thresholds': thresholds,
    'distances': distances,
    'labels': labels
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from lixiaotong97/DSU
pointer only; the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get Ran
ran; our contract draft was wrong, not the code
prajual/Deep_Speaker/models.py
code served (permissive licence) · get_code("2cbf4ce7e0235a0d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned MockLayerObject. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import logging

class MockLayerObject:
    def __init__(self, name):
        self.name = name

obj = MockLayerObject("test_layer")

ARGS = {
    "obj": obj
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockLayerObject — a MockLayerObject output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockLayerObject output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
getwavPathAndwavLabel Ran
ran; our contract draft was wrong, not the code
wangleiai/dVectorSpeakerRecognition/kersaSoftmax/dnnTrain.py
pointer only (licence: NONE) · get_code("cbc4d3a4f90e8027")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangleiai/dVectorSpeakerRecognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getwavPathAndwavLabel Ran
ran; our contract draft was wrong, not the code
wangleiai/dVectorSpeakerRecognition/kersaSoftmax/gruTrain.py
pointer only (licence: NONE) · get_code("9e35c18ce8eaf604")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangleiai/dVectorSpeakerRecognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_scores Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Walleclipse/Deep_Speaker-speaker_recognition_system/test_model.py
pointer only (licence: NONE) · get_code("6a6418cda28d6455")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Walleclipse/Deep_Speaker-speaker_recognition_system when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_optimizer Not yet run
unverified (harvested, no recorded run)
qqueing/DeepSpeaker-pytorch/train_triplet.py
code served (permissive licence) · get_code("d74d2593f3b8926c")
How it ran

no invocation recorded.

evaluate Not yet run
unverified (harvested, no recorded run)
qqueing/DeepSpeaker-pytorch/eval_metrics.py
code served (permissive licence) · get_code("1283b5c46e6830d4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
23 dated earlier, 663 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
calculate_accuracy 12 other papers
3 dated earlier, 9 later
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1607.08221 (2016-07)
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
1703.07737 (2017-03)
In Defense of the Triplet Loss for Person Re-Identification
and 9 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1705.02304")
get_code_for_paper("1705.02304")
have("1705.02304")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1705.02304.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1705.02304.svg)](https://syntology.ai/paper/1705.02304)

Connect an agent — have() is free.