SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.09296 · ICML · 2021

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Pin-Yu Chen, Chao-Han Huck, Yun-Yun Tsai, Chao-Han Yang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 6 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/2106.09296.json · badge: /api/ran/2106.09296.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
huckiyang/Voice2Series-Reprogramming canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
dodohow1011/speechadvreprogram community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
ARTLayer Ran
ran on a synthesized input · constructed an object; no result was computed
huckiyang/Voice2Series-Reprogramming/ts_model.py
code served (permissive licence) · get_code("153caf7d3bfcd33b")
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 an instance of its own class, ARTLayer: the run constructed the object and did not call it, so no result was computed. 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 tensorflow as tf
import numpy as np
from tensorflow.keras.layers import Layer

# Create a minimal input for testing
# The ARTLayer expects 3D input based on build assertion: len(input_shape) == 3
# We'll create a small batch of sequences

batch_size = 2
sequence_length = 5
feature_dim = 4

# Create a dummy input tensor with shape (batch_size, sequence_length, feature_dim)
dummy_input = tf.random.normal((batch_size, sequence_length, feature_dim))

# Define the parameters for ARTLayer
tar_1ds = 100  # target 1D size, used in masking matrix construction
mod = 0  # modality: 0 for simple masking, 1 for center padding
drop_rate = 0.4  # dropout rate
W_regularizer = 0.05  # L2 regularization weight

# Build the layer
art_layer = tf.keras.layers.Layer.__new__(type('ARTLayer', (Layer,), {}))

# Now construct ARGS dict with all parameters
ARGS = {
    'tar_1ds': tar_1ds,
    'mod': mod,
    'drop_rate': drop_rate,
    'W_regularizer': W_regularizer,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ARTLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ARTLayer 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
ARTLayer Not yet run
unverified (harvested, no recorded run)
dodohow1011/speechadvreprogram/ts_model.py
pointer only (licence: NONE) · get_code("9accaf09272fa8de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dodohow1011/speechadvreprogram 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. No invocation recorded.

SegZeroPadding1D Not yet run
unverified (harvested, no recorded run)
huckiyang/Voice2Series-Reprogramming/ts_model.py
code served (permissive licence) · get_code("dd2707972254321a")
How it ran

no invocation recorded.

WARTmodel Not yet run
unverified (harvested, no recorded run)
huckiyang/Voice2Series-Reprogramming/ts_model.py
code served (permissive licence) · get_code("842dae934f36948c")
How it ran

no invocation recorded.

WARTmodel Not yet run
unverified (harvested, no recorded run)
dodohow1011/speechadvreprogram/ts_model.py
pointer only (licence: NONE) · get_code("357bdf0c9486647f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dodohow1011/speechadvreprogram 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. No invocation recorded.

multi_mapping Not yet run
unverified (harvested, no recorded run)
huckiyang/Voice2Series-Reprogramming/ts_model.py
code served (permissive licence) · get_code("096ee24533130aea")
How it ran

no invocation recorded.

multi_mapping Not yet run
unverified (harvested, no recorded run)
dodohow1011/speechadvreprogram/ts_model.py
pointer only (licence: NONE) · get_code("0f90ec13976b2e46")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dodohow1011/speechadvreprogram 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. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 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.

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

Learning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper, we propose Voice2Series (V2S), a novel end-toend approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 30 different time series tasks we show that V2S performs competitive results on 19 time series classification tasks. We further provide a theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification. Our code of is available at https://github.com/huckiyang/ Voice2Series-Reprogramming.

For agents

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

get_harvested_code_for_paper("2106.09296")
get_code_for_paper("2106.09296")
have("2106.09296")

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

curl https://syntology.ai/api/ran/2106.09296.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.09296.svg)](https://syntology.ai/paper/2106.09296)

Connect an agent — have() is free.