SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.06247 · 2019

End-to-End Neural Speaker Diarization with Self-attention

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 0 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/1909.06247.json · badge: /api/ran/1909.06247.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
JunzheJosephZhu/EEND-for-LENA community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
get_input_dim Ran
ran on a synthesized input
JunzheJosephZhu/EEND-for-LENA/eend/feature.py
code served (permissive licence) · get_code("2f299371003065aa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - frame_size: int, used in bit_length() and arithmetic
# - context_size: int, used in arithmetic
# - transform_type: str, used with startswith()

# Construct valid arguments
frame_size = 8
context_size = 5
transform_type = 'logmel23'

ARGS = {
    'frame_size': frame_size,
    'context_size': context_size,
    'transform_type': transform_type
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
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
load_segments Ran
ran on a synthesized input
JunzheJosephZhu/EEND-for-LENA/eend/kaldi_data.py
code served (permissive licence) · get_code("216dff0f296d027f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 os
import numpy as np
import tempfile

# Create a temporary segments file with valid data
temp_dir = tempfile.mkdtemp()
segments_file = os.path.join(temp_dir, "segments.txt")

# Write sample segment data in the format expected by loadtxt
with open(segments_file, 'w') as f:
    f.write("utt_001 rec_001 0.5 1.5\n")
    f.write("utt_002 rec_002 2.0 3.5\n")

ARGS = {
    'segments_file': segments_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
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
load_segments_hash Ran
ran on a synthesized input
JunzheJosephZhu/EEND-for-LENA/eend/kaldi_data.py
code served (permissive licence) · get_code("805c93ef8140e802")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. 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 os
import tempfile

# Create a temporary segments file
temp_dir = tempfile.mkdtemp()
segments_file = os.path.join(temp_dir, "segments.txt")

# Write sample segment data
with open(segments_file, 'w') as f:
    f.write("utt1 rec1 0.0 1.5\n")
    f.write("utt2 rec1 1.5 3.2\n")
    f.write("utt3 rec2 0.5 2.1\n")

ARGS = {
    "segments_file": segments_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_segments_rechash Ran
ran on a synthesized input
JunzheJosephZhu/EEND-for-LENA/eend/kaldi_data.py
code served (permissive licence) · get_code("11ff0f39a6fdcd1e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. 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 os
import tempfile

# Create a temporary segments file with test data
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt') as f:
    f.write("utt1 rec1 0.0 1.5\n")
    f.write("utt2 rec1 1.5 3.0\n")
    f.write("utt3 rec2 0.5 2.0\n")
    segments_file_path = f.name

ARGS = {
    "segments_file": segments_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
subsample Ran
ran on a synthesized input
JunzheJosephZhu/EEND-for-LENA/eend/feature.py
code served (permissive licence) · get_code("08f6950bcdfafc26")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. 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 torch
import numpy as np

torch.manual_seed(0)

# Y should be a tensor or array-like that supports slicing with [::]
# T should be a tensor or array-like that supports slicing with [::]
# subsampling is an integer that controls the step size

Y = torch.randn(8, 4)  # 8 frames, 4 features
T = torch.randn(8, 3)  # 8 frames, 3 different dimension

ARGS = {
    "Y": Y,
    "T": T,
    "subsampling": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
load_segments 2 other papers
2 later
2005.09921 (2020-05)
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
2006.01796 (2020-06)
Neural Speaker Diarization with Speaker-Wise Chain Rule
load_segments_hash 2 other papers
2 later
2005.09921 (2020-05)
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
2006.01796 (2020-06)
Neural Speaker Diarization with Speaker-Wise Chain Rule
load_segments_rechash 2 other papers
2 later
2005.09921 (2020-05)
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
2006.01796 (2020-06)
Neural Speaker Diarization with Speaker-Wise Chain Rule
subsample 2 other papers
2 later
2005.09921 (2020-05)
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
2006.01796 (2020-06)
Neural Speaker Diarization with Speaker-Wise Chain Rule
get_input_dim 1 other paper
1 later
2005.09921 (2020-05)
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors

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

Speaker diarization has been mainly developed based on the clustering of speaker embeddings. However, the clustering-based approach has two major problems; i.e., (i) it is not optimized to minimize diarization errors directly, and (ii) it cannot handle speaker overlaps correctly. To solve these problems, the End-to-End Neural Diarization (EEND), in which a bidirectional long short-term memory (BLSTM) network directly outputs speaker diarization results given a multi-talker recording, was recently proposed. In this study, we enhance EEND by introducing self-attention blocks instead of BLSTM blocks. In contrast to BLSTM, which is conditioned only on its previous and next hidden states, self-attention is directly conditioned on all the other frames, making it much suitable for dealing with the speaker diarization problem. We evaluated our proposed method on simulated mixtures, real telephone calls, and real dialogue recordings. The experimental results revealed that the self-attention was the key to achieving good performance and that our proposed method performed significantly better than the conventional BLSTM-based method. Our method was even better than that of the state-of-the-art x-vector clustering-based method. Finally, by visualizing the latent representation, we show that the self-attention can capture global speaker characteristics in addition to local speech activity dynamics. Our source code is available online at https://github.com/hitachi-speech/EEND.

For agents

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

get_harvested_code_for_paper("1909.06247")
get_code_for_paper("1909.06247")
have("1909.06247")

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

curl https://syntology.ai/api/ran/1909.06247.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.06247.svg)](https://syntology.ai/paper/1909.06247)

Connect an agent — have() is free.