Papers › Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech

26 Feb 2024arXiv:2402.16321archive 2025-07-28

Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao, Yu-Chiang Frank Wang

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE). The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. To further improve correlation with real quality scores, domain knowledge of speech processing is incorporated into the model design. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training. To improve the robustness of the encoder for SE, a novel self-distillation mechanism combined with adversarial training is introduced. In summary, the proposed speech quality estimation method and enhancement models require only clean speech for training without any label requirements. Experimental results show that the proposed VQScore and enhancement model are competitive with supervised baselines. The code will be released after publication.

PaperPDFCodeCode Syntology ranMethod as code

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 11 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 5 ran (2 with no instrument failure; 3 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 5 samples that ran have no recorded date.

JasonSWFu/VQscore officialpytorchSyntology: 11 samples, 5 ran (3 instrument-failed) · 6 unverified 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.

Code Syntology ran Syntology

11 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran
6unverified

Licence: 11 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from JasonSWFu/VQscore. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

JasonSWFu/VQscore official repository 11 samples, 5 ran (3 instrument-failed) · 6 unverified
CNN_1D_decoder_QE models/VQVAE_models.py ran · metamorphic tier: invariant no licence file found · pointer only · b8a0165c23a73cb3 · report fixture: signature zq:Tensor/3/float · returned Tensor · level recorded 2026-09-22
CNN_1D_encoder_QE models/VQVAE_models.py ran no licence file found · pointer only · 9e5d56abc2a08a53 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
cos_loss inference.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 56de883df56b1fbb · report fixture: signature SP_noisy:Tensor/2/float, SP_y_noisy:Tensor/2/float · returned Tensor · level recorded, date not recorded
gumbel_sample in 15 papers
census: 6 implementations from 5 papers, 2 distinct outputs on one shared input
models/VQVAE_models.py ran · our draft was wrong no licence file found · pointer only · fb5ef568d9dbf7b5 · report fixture: signature distance:Tensor/2/float, temperature:float/0/float, stochastic:bool/0/bool, straight_through:bool/0/bool, reinmax:bool/0/bool, dim:int/0/int, training:bool/0/bool · returned tuple · level recorded 2026-09-22
stft_magnitude in 8 papers inference.py ran · our draft was wrong no licence file found · pointer only · c05fc59409ba925c · report fixture: signature x:Tensor/2/float, hop_size:int/0/int, fft_size:int/0/int, win_length:int/0/int · returned Tensor · level recorded, date not recorded
CNN_1D_quantizer_QE models/VQVAE_models.py unverified no licence file found · pointer only · 1ccf86e8795fed3b · report
CosineSimCodebook in 5 papers models/VQVAE_models.py unverified no licence file found · pointer only · f8e325b49ff91a19 · report
EuclideanCodebook in 6 papers models/VQVAE_models.py unverified no licence file found · pointer only · 252f6a2a01339c05 · report
VQVAE_QE models/VQVAE_models.py unverified no licence file found · pointer only · e7029fcc1359a25e · report
VectorQuantize in 6 papers models/VQVAE_models.py unverified no licence file found · pointer only · 23568f6dd68bbe9b · report
resynthesize inference.py unverified no licence file found · pointer only · fb486c5b29adc71b · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for VQScore (graph method: VQScore). 31 bricks; individually on a fixture: 20 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 14 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. VQVAE_QE entry · level 0 · unverified · e7029fcc1359a25e
  2. CNN_1D_decoder_QE model · level 1 · ran · b8a0165c23a73cb3
  3. CNN_1D_encoder_QE model · level 1 · ran · 9e5d56abc2a08a53
  4. CNN_1D_quantizer_QE model · level 0 · unverified · 1ccf86e8795fed3b
  5. VectorQuantize model · level 0 · unverified · 23568f6dd68bbe9b
  6. CosineSimCodebook helper · level 0 · unverified · f8e325b49ff91a19
  7. EuclideanCodebook helper · level 0 · unverified · 252f6a2a01339c05
  8. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  9. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  10. gumbel_sample helper · level 1 · ran · our draft was wrong · fb5ef568d9dbf7b5
  11. identity helper · level 1 · ran · honoured contract · f3232418205f7cbd
  12. orthogonal_loss_fn helper · level 1 · ran; the contract check could not run · 527a2ecf26715268
  13. pack_one helper · level 0 · unverified · 9adcac32b9f87dfb
  14. unpack_one helper · level 0 · unverified · 95a567bd7c1ffdce
  15. batched_embedding helper · level 1 · ran; the contract check could not run · 4dc1339e961ab500
  16. batched_sample_vectors helper · level 1 · ran; the contract check could not run · c1c89ffd41de10bb
  17. ema_inplace helper · level 0 · unverified · fda38ab65bb996a9
  18. kmeans helper · level 1 · ran · our draft was wrong · e139cdc24aa46838
  19. l2norm helper · level 1 · ran · our draft was wrong · eca6cdf05972a95e
  20. laplace_smoothing helper · level 1 · ran · our draft was wrong · 702d64c397294ae2
  21. noop helper · level 0 · unverified · 02dd009b7cb924bb
  22. sample_vectors_distributed helper · level 1 · ran; the contract check could not run · ecf368eff22730c4
  23. uniform_init helper · level 0 · unverified · f9a12a99a3e74bc8
  24. gumbel_noise helper · level 1 · ran · honoured contract · d85a55ec5c2984ef
  25. sample_vectors helper · level 1 · ran; the contract check could not run · ada1d74afbd92171
  26. batched_bincount helper · level 1 · ran · our draft was wrong · 309924b930360692
  27. all_gather_sizes helper · level 0 · unverified · cee1bd208302c3f3
  28. all_gather_variably_sized helper · level 1 · ran; the contract check could not run · 2e60cd798dd2182c
  29. sample_multinomial helper · level 1 · ran · our draft was wrong · cf379aef60d216c3
  30. log helper · level 2 · ran · our draft was wrong · b5472673332de78e
  31. pad_shape helper · level 1 · ran; the contract check could not run · 64ec7553b1fd0e74

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2402.16321") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

QuantizationSpeech Enhancement

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

VQ-VAE

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