SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.07078 · 2019

Semantic query-by-example speech search using visual grounding

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 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/1904.07078.json · badge: /api/ran/1904.07078.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
kamperh/flickr_semantic_qbe_eval community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_eer Ran
ran on a synthesized input
kamperh/flickr_semantic_qbe_eval/eval_semantic_qbe.py
code served (permissive licence) · get_code("55b745ff3d7b3330")
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 float, ndim 0, dtype family float, 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 numpy as np
from scipy.interpolate import interp1d
from scipy.optimize import brentq
import sklearn.metrics as metrics

# Create synthetic binary classification data
np.random.seed(0)

# y_true: binary labels (0 or 1)
y_true = np.array([0, 0, 1, 1, 0, 1, 0, 1])

# y_score: confidence scores or probabilities for the positive class
# Should be between 0 and 1
y_score = np.array([0.1, 0.2, 0.8, 0.9, 0.15, 0.85, 0.25, 0.75])

ARGS = {
    "y_true": y_true,
    "y_score": y_score,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, 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
eval_qbe Ran
ran on a synthesized input
kamperh/flickr_semantic_qbe_eval/eval_semantic_qbe.py
code served (permissive licence) · get_code("542e7c5d114c0d4a")
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, 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

# Analyze the function to understand what structures are needed:
# - cost_dict: dict where keys are query_keys (format: 'keyword_...')
#   values are dicts mapping utt_keys to scores (floats)
# - label_dict: dict where keys are utt_keys, values are lists/sets of keywords
# - analyse: boolean flag (optional)

# Create a small test dataset
keyword1 = "cat"
keyword2 = "dog"

# Create query keys (format: keyword_queryid)
query_key_1 = f"{keyword1}_query_1"
query_key_2 = f"{keyword1}_query_2"
query_key_3 = f"{keyword2}_query_1"

# Create utterance keys
utt_keys = ["utt_001", "utt_002", "utt_003", "utt_004", "utt_005"]

# Build cost_dict: maps query_key -> {utt_key -> score}
# scores should be distances/costs (lower is better, so we negate them for y_score)
cost_dict = {
    query_key_1: {
        "utt_001": 0.1,
        "utt_002": 0.3,
        "utt_003": 0.5,
        "utt_004": 0.7,
        "utt_005": 0.9,
    },
    query_key_2: {
        "utt_001": 0.2,
        "utt_002": 0.4,
        "utt_003": 0.6,
        "utt_004": 0.8,
        "utt_005": 0.95,
    },
    query_key_3: {
        "utt_001": 0.15,
        "utt_002": 0.35,
        "utt_003": 0.55,
        "utt_004": 0.75,
        "utt_005": 0.85,
    },
}

# Build label_dict: maps utt_key -> list of keywords it contains
label_dict = {
    "utt_001": [keyword1],
    "utt_002": [keyword1, keyword2],
    "utt_003": [keyword2],
    "utt_004": [keyword1],
    "utt_005": [],
}

ARGS = {
    "cost_dict": cost_dict,
    "label_dict": label_dict,
    "analyse": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn, tqdm — 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
get_captions_dict Ran
ran on a synthesized input
kamperh/flickr_semantic_qbe_eval/eval_semantic_qbe.py
code served (permissive licence) · get_code("a8deef93e78a325c")
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 tempfile
import os

# Create a temporary file with caption data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("image1 the quick brown fox jumps\n")
temp_file.write("image2 over the lazy dog <tag> 'quoted'\n")
temp_file.write("image3 a b c d e f\n")
temp_file.close()

ARGS = {
    'captions_fn': temp_file.name
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode retrieval. Here we consider how such models can be used for query-by-example (QbE) search, the task of retrieving utterances relevant to a given spoken query. We are particularly interested in semantic QbE, where the task is not only to retrieve utterances containing exact instances of the query, but also utterances whose meaning is relevant to the query. We follow a segmental QbE approach where variable-duration speech segments (queries, search utterances) are mapped to fixed-dimensional embedding vectors. We show that a QbE system using an embedding function trained on visually grounded speech data outperforms a purely acoustic QbE system in terms of both exact and semantic retrieval performance.

For agents

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

get_harvested_code_for_paper("1904.07078")
get_code_for_paper("1904.07078")
have("1904.07078")

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

curl https://syntology.ai/api/ran/1904.07078.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.07078.svg)](https://syntology.ai/paper/1904.07078)

Connect an agent — have() is free.