SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.04448 · 2019

Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/1907.04448.json · badge: /api/ran/1907.04448.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
Jeevesh8/Cross-Lingual-Voice-Cloning community (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
PaddlePaddle/DeepSpeech community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
dynamic_range_compression Ran
ran; our contract draft was wrong, not the code
Jeevesh8/Cross-Lingual-Voice-Cloning/audio_processing.py
pointer only (licence: BSD-3-Clause) · get_code("83e2c862f7374ac7")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

grad_reverse Ran
ran on a synthesized input
Jeevesh8/Cross-Lingual-Voice-Cloning/gradient_reversal.py
pointer only (licence: BSD-3-Clause) · get_code("63cd61beeb29c53c")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

griffin_lim Ran
ran; our contract draft was wrong, not the code
Jeevesh8/Cross-Lingual-Voice-Cloning/audio_processing.py
pointer only (licence: BSD-3-Clause) · get_code("9f9ec26d4cdfdf7d")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

rectify Ran
ran on a synthesized input
PaddlePaddle/DeepSpeech/utils/DER.py
code served (permissive licence) · get_code("370f5007edfb630b")
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 2, dtype family float, shape (2, 4) 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

# Create a test array with various values including NaN and Inf
arr = np.array([
    [0.5, np.nan, 0.3, 0.8],
    [0.1, 0.9, np.inf, 0.4]
], dtype=np.float32)

ARGS = {
    "arr": arr
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
DER Not yet run
unverified (harvested, no recorded run)
PaddlePaddle/DeepSpeech/utils/DER.py
code served (permissive licence) · get_code("46c1836d242e90f0")
How it ran

no invocation recorded.

apply_gradient_allreduce Not yet run
unverified (harvested, no recorded run)
Jeevesh8/Cross-Lingual-Voice-Cloning/distributed.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from kttrcdl/umetts, is pointer only (licence: GPL-2.0) · get_code("f7bf9f0265e33cf0")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

plot_alignment_to_numpy Not yet run
unverified (harvested, no recorded run)
Jeevesh8/Cross-Lingual-Voice-Cloning/plotting_utils.py
pointer only (licence: BSD-3-Clause) · get_code("3d89a23ee4d0b639")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

plot_spectrogram_to_numpy Not yet run
unverified (harvested, no recorded run)
Jeevesh8/Cross-Lingual-Voice-Cloning/plotting_utils.py
pointer only (licence: BSD-3-Clause) · get_code("2545971684f8134d")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

save_figure_to_numpy Not yet run
unverified (harvested, no recorded run)
Jeevesh8/Cross-Lingual-Voice-Cloning/plotting_utils.py
pointer only (licence: BSD-3-Clause) · get_code("29d749e3e95fa41d")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, Jeevesh8/Cross-Lingual-Voice-Cloning, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. 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, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 7 later) and 2 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
griffin_lim 14 other papers
3 dated earlier, 11 later
1803.09017 (2018-03)
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
1811.02122 (2018-11)
Robust and fine-grained prosody control of end-to-end speech synthesis
1812.04342 (2018-12)
Learning latent representations for style control and transfer in end-to-end speech synthesis
and 11 more not named here
dynamic_range_compression 13 other papers
4 dated earlier, 9 later
1803.09017 (2018-03)
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
1811.02122 (2018-11)
Robust and fine-grained prosody control of end-to-end speech synthesis
1812.04342 (2018-12)
Learning latent representations for style control and transfer in end-to-end speech synthesis
and 10 more not named here
apply_gradient_allreduce 5 other papers
2 dated earlier, 3 later
1811.02122 (2018-11)
Robust and fine-grained prosody control of end-to-end speech synthesis
1812.04342 (2018-12)
Learning latent representations for style control and transfer in end-to-end speech synthesis
1909.11646 (2019-09)
High Fidelity Speech Synthesis with Adversarial Networks
and 2 more not named here
save_figure_to_numpy 4 other papers
4 later
2005.05957 (2020-05)
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
2212.14518 (2022-12)
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
and 1 more not named here
plot_alignment_to_numpy 2 other papers
2 later
2005.05957 (2020-05)
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
plot_spectrogram_to_numpy 1 other paper
1 later
2106.06103 (2021-06)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
rectify 1 other paper
1 later
2306.15354 (2023-06)
3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement

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 2026-11-21.

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 a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across languages, e.g. synthesize fluent Spanish speech using an English speaker's voice, without training on any bilingual or parallel examples. Such transfer works across distantly related languages, e.g. English and Mandarin. Critical to achieving this result are: 1. using a phonemic input representation to encourage sharing of model capacity across languages, and 2. incorporating an adversarial loss term to encourage the model to disentangle its representation of speaker identity (which is perfectly correlated with language in the training data) from the speech content. Further scaling up the model by training on multiple speakers of each language, and incorporating an autoencoding input to help stabilize attention during training, results in a model which can be used to consistently synthesize intelligible speech for training speakers in all languages seen during training, and in native or foreign accents.

For agents

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

get_harvested_code_for_paper("1907.04448")
get_code_for_paper("1907.04448")
have("1907.04448")

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

curl https://syntology.ai/api/ran/1907.04448.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.04448.svg)](https://syntology.ai/paper/1907.04448)

Connect an agent — have() is free.