Papers › XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech

31 May 2023arXiv:2305.19709archive 2025-07-28

Linh The Nguyen, Thinh Pham, Dat Quoc Nguyen

We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. We publicly release our pre-trained XPhoneBERT with the hope that it would facilitate future research and downstream TTS applications for multiple languages. Our XPhoneBERT model is available at https://github.com/VinAIResearch/XPhoneBERT

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 14 ran (12 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vinairesearch/xphonebert officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 14 ran (2 instrument-failed) · 4 unverified report
yl4579/StyleTTS2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial... (arXiv:2306.07691; that paper's own run record: 0 ran · 4 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
10ran
4unverified

Licence: 10 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 10 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from vinairesearch/xphonebert. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

vinairesearch/xphonebert official repository 18 samples, 14 ran (2 instrument-failed) · 4 unverified
convert_pad_shape in 15 papers VITS_with_XPhoneBERT/commons.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 59ae0708b1e8d94b · report fixture: signature pad_shape:list/1/list · returned list · level recorded 2026-09-22
discriminator_loss in 38 papers VITS_with_XPhoneBERT/losses.py ran MIT (permissive) here; the stored copy is pointer only · 896f7aae82a62114 · report fixture: signature disc_real_outputs:list/1/Tensor, disc_generated_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-26
dynamic_range_compression_torch in 9 papers VITS_with_XPhoneBERT/mel_processing.py ran fingerprinted MIT (permissive) · 262807b9eb9706a5 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-26
dynamic_range_decompression_torch in 5 papers VITS_with_XPhoneBERT/mel_processing.py ran fingerprinted MIT (permissive) · 78c12e563d5af53d · report fixture: signature x:Tensor/2/float, C:int/0/int · returned Tensor · level recorded 2026-09-26
expand_abbreviations in 10 papers VITS_with_XPhoneBERT/text/cleaners.py ran fingerprinted MIT (permissive) · cea1f83e9db28ed8 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
feature_loss in 27 papers VITS_with_XPhoneBERT/losses.py ran MIT (permissive) here; the stored copy is pointer only · 24e8b4731dc3e070 · report fixture: signature fmap_r:list/1/list, fmap_g:list/1/list · returned Tensor · level recorded 2026-09-26
generator_loss in 32 papers VITS_with_XPhoneBERT/losses.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 6191fd9efbdd55d4 · report fixture: signature disc_outputs:list/1/Tensor · returned tuple · level recorded 2026-09-26
get_padding in 84 papers VITS_with_XPhoneBERT/commons.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · a26f85d7c72ef39a · report fixture: signature kernel_size:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
intersperse in 14 papers VITS_with_XPhoneBERT/commons.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c01a3efb274ff778 · report fixture: signature lst:list/1/int, item:int/0/int · returned list · level recorded 2026-09-26
latest_checkpoint_path in 9 papers VITS_with_XPhoneBERT/utils.py ran MIT (permissive) here; the stored copy is pointer only · 321604dda57bb02d · report fixture: signature dir_path:str/0/str, regex:str/0/str · returned str · level recorded 2026-09-24
load_checkpoint in 277 papers VITS_with_XPhoneBERT/utils.py ran MIT (permissive) here; the stored copy is pointer only · c647283e53cacacf · report fixture: signature checkpoint_path:str/0/str, model:callable/0/?, optimizer:Adam/0/? · returned tuple · level recorded 2026-09-24
lowercase in 9 papers VITS_with_XPhoneBERT/text/cleaners.py ran fingerprinted MIT (permissive) · 296274b940cb0b32 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
spectral_normalize_torch in 8 papers VITS_with_XPhoneBERT/mel_processing.py ran fingerprinted MIT (permissive) · 26b87488d429896a · report fixture: signature magnitudes:Tensor/2/float · returned Tensor · level recorded 2026-09-26
unconstrained_rational_quadratic_spline in 8 papers VITS_with_XPhoneBERT/transforms.py ran MIT (permissive) here; the stored copy is pointer only · 70a7614b3b3eb41f · report fixture: signature inputs:Tensor/1/float, unnormalized_widths:Tensor/2/float, unnormalized_heights:Tensor/2/float, unnormalized_derivatives:Tensor/2/float, inverse:bool/0/bool, tails:str/0/str, tail_bound:float/0/float, min_bin_width:float/0/float, min_bin_height:float/0/float, min_derivative:float/0/float · returned tuple · level recorded 2026-09-24
expand_numbers in 5 papers VITS_with_XPhoneBERT/text/cleaners.py unverified MIT (permissive) · 4c6716f6a3894fe8 · report
piecewise_rational_quadratic_transform in 8 papers VITS_with_XPhoneBERT/transforms.py unverified MIT (permissive) here; the stored copy is pointer only · ba6cafc4d658c14f · report
plot_spectrogram_to_numpy in 8 papers VITS_with_XPhoneBERT/utils.py unverified MIT (permissive) · d1de5b72a4f78810 · report
searchsorted in 9 papers VITS_with_XPhoneBERT/transforms.py unverified MIT (permissive) · e85d747983c4f5d8 · report

Tasks

Text to Speechtext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionRoBERTaSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections