Papers › LightHuBERT: Lightweight and Configurable Speech Representation Learning with...

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

29 Mar 2022arXiv:2203.15610archive 2025-07-28

Rui Wang, Qibing Bai, Junyi Ao, Long Zhou, Zhixiang Xiong, Zhihua Wei, Yu Zhang, Tom Ko, Haizhou Li

Self-supervised speech representation learning has shown promising results in various speech processing tasks. However, the pre-trained models, e.g., HuBERT, are storage-intensive Transformers, limiting their scope of applications under low-resource settings. To this end, we propose LightHuBERT, a once-for-all Transformer compression framework, to find the desired architectures automatically by pruning structured parameters. More precisely, we create a Transformer-based supernet that is nested with thousands of weight-sharing subnets and design a two-stage distillation strategy to leverage the contextualized latent representations from HuBERT. Experiments on automatic speech recognition (ASR) and the SUPERB benchmark show the proposed LightHuBERT enables over 10⁹ architectures concerning the embedding dimension, attention dimension, head number, feed-forward network ratio, and network depth. LightHuBERT outperforms the original HuBERT on ASR and five SUPERB tasks with the HuBERT size, achieves comparable performance to the teacher model in most tasks with a reduction of 29% parameters, and obtains a 3.5× compression ratio in three SUPERB tasks, e.g., automatic speaker verification, keyword spotting, and intent classification, with a slight accuracy loss. The code and pre-trained models are available at https://github.com/mechanicalsea/lighthubert.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.15610")

Code

Syntology Ran 1 of 8 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 8 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mechanicalsea/lighthubert officialmentioned in papermentioned on GitHubpytorchMIT 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

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
7unverified

Licence: 0 of the 8 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 mechanicalsea/lighthubert. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

quant_noise mechanicalsea/lighthubert/lighthubert/modules/fairseq_modules.py official repository ran · our draft was wrong MIT (permissive) · 50d074f5c3f3407d · report
compute_mask_indices mechanicalsea/lighthubert/lighthubert/lighthubert.py official repository unverified MIT (permissive) · 6eeb1f787769a05e · report
index_put mechanicalsea/lighthubert/lighthubert/functional/fairseq_utils.py official repository unverified MIT (permissive) · 28bed6ccb2f1b89a · report
is_xla_tensor mechanicalsea/lighthubert/lighthubert/functional/fairseq_utils.py official repository unverified MIT (permissive) · 29c1031dcedd09de · report
mask_padding mechanicalsea/lighthubert/lighthubert/functional/sliding_attn.py official repository unverified MIT (permissive) · d48916e1aac4a4de · report
merge_padding_attm_mask mechanicalsea/lighthubert/lighthubert/functional/sliding_attn.py official repository unverified MIT (permissive) · fb33b4608f21a92a · report
pad_as_attn_swz mechanicalsea/lighthubert/lighthubert/functional/sliding_attn.py official repository unverified MIT (permissive) · 3bbfd682fbeb9a6d · report
pad_to_multiple mechanicalsea/lighthubert/lighthubert/functional/fairseq_utils.py official repository unverified MIT (permissive) · b57d92d8a18d12a3 · report

Tasks

AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Intent ClassificationKeyword SpottingRepresentation LearningSpeaker VerificationSpeech RecognitionSpeech Representation Learningintent-classificationspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerPruningResidual ConnectionSoftmaxTransformer

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