Browse › Audio › Speech Recognition › LibriSpeech test-clean

Speech Recognition archive 2025-07-28

LibriSpeech test-clean Benchmark (Speech Recognition)

64 rows 45 with code listed 1 metric Dataset page

Syntology Since the archive (Syntology): none placed; 18 newer papers judged to report on this board so far.

Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.

The archive carries no text for this table; the description above is the archive's text for the task Speech Recognition. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: Word Error Rate (WER) (lower is better). Points are placed at the row's paper date, not an evaluation date; 60 of 64 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 United Med ASR 0.985 ✓ Paper – 2024 no code linked report
2 SAMBA ASR 1.17 ✓ Paper – 2025 no code linked report
3 FAdam 1.34 ✓ Paper Code 2024 linked, not harvested report
4 Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light 1.4 ✓ Paper Code 2020 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
5 w2v-BERT XXL 1.4 ✓ Paper Code 2021 linked, not harvested report
6 parakeet-rnnt-1.1b 1.46 ✓ Paper – 2023 no code linked report
7 Conv + Transformer + wav2vec2.0 + pseudo labeling 1.5 ✓ Paper Code 2020 linked, not harvested report
8 ContextNet + SpecAugment-based Noisy Student Training with Libri-Light 1.7 ✓ Paper Code 2020 linked, not harvested report
9 SpeechStew (1B) 1.7 ✓ Paper – 2021 no code linked report
10 Multistream CNN with Self-Attentive SRU (WER includes text normalization) 1.75 ✓ Paper – 2020 no code linked report
11 Stateformer 1.76 – Paper – 2023 no code linked report
12 wav2vec 2.0 with Libri-Light 1.8 ✓ Paper Code 2020 community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified report
13 HuBERT with Libri-Light 1.8 ✓ Paper Code 2021 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified report
14 WavLM Large 1.8 – Paper Code 2021 linked, not harvested report
15 E-Branchformer (L) + Internal Language Model Estimation 1.81 – Paper Code 2022 linked, not harvested report
16 Zipformer+pruned transducer w/ CR-CTC (no external language model) 1.88 – Paper Code 2024 linked, not harvested report
17 ContextNet(L) 1.9 – Paper Code 2020 linked, not harvested report
18 Conformer(L) 1.9 – Paper Code 2020 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
19 Transformer+Time reduction+Self Knowledge distillation 1.9 – Paper – 2021 no code linked report
20 ContextNet(M) 2 ✓ Paper Code 2020 linked, not harvested report
21 Transformer Transducer 2.0 – Paper Code 2020 linked, not harvested report
22 Conformer(M) 2 ✓ Paper Code 2020 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
23 SpeechStew (100M) 2.0 – Paper – 2021 no code linked report
24 Qwen-Audio 2.0 – Paper Code 2023 official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified report
25 Zipformer+pruned transducer (no external language model) 2.00 – Paper Code 2023 linked, not harvested report
26 Zipformer+CR-CTC (no external language model) 2.02 – Paper Code 2024 linked, not harvested report
27 Conv + Transformer AM + Pseudo-Labeling (ConvLM with Transformer Rescoring) 2.03 – Paper Code 2019 linked, not harvested report
28 Conv + Transformer AM + Iterative Pseudo-Labeling (n-gram LM + Transformer Rescoring) 2.10 – Paper Code 2020 linked, not harvested report
29 CTC + Transformer LM rescoring 2.10 – Paper – 2020 no code linked report
30 Conformer(S) 2.1 – Paper Code 2020 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
31 Branchformer + GFSA 2.11 – Paper Code 2023 official (archive's flag): 6 ran · 22 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 5 violated, 4 with no contract checked; 11 where Syntology's instrument failed) · 7 unverified report
32 Multi-Stream Self-Attention With Dilated 1D Convolutions 2.20 – Paper Code 2019 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
33 LSTM Transducer 2.23 ✓ Paper Code 2021 linked, not harvested report
34 Hybrid + Transformer LM rescoring 2.26 – Paper – 2019 no code linked report
35 Hybrid model with Transformer rescoring 2.3 – Paper Code 2019 linked, not harvested report
36 ContextNet(S) 2.3 ✓ Paper Code 2020 linked, not harvested report
37 Conv + Transformer AM (ConvLM with Transformer Rescoring) (LS only) 2.31 – Paper Code 2019 linked, not harvested report
38 Squeezeformer (L) 2.47 – Paper Code 2022 official (archive's flag): 5 ran · 31 ran (of which 12 constructed an object rather than computing a result; 28 with no instrument failure: 3 honoured, 0 violated, 25 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified report
39 LAS + SpecAugment 2.5 ✓ Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified report
40 Transformer 2.6 ✓ Paper Code 2019 linked, not harvested report
41 QuartzNet15x5 2.69 – Paper Code 2019 community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
42 LAS (no LM) 2.7 ✓ Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified report
43 wav2vec_wav2letter 2.7 – Paper Code 2020 linked, not harvested report
44 Espresso 2.8 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
45 Jasper DR 10x5 (+ Time/Freq Masks) 2.84 – Paper Code 2019 linked, not harvested report
46 Jasper DR 10x5 2.95 – Paper Code 2019 linked, not harvested report
47 tdnn + chain + rnnlm rescoring 3.06 – Paper – 2018 no code linked report
48 Convolutional Speech Recognition 3.26 ✓ Paper – 2018 no code linked report
49 MT4SSL 3.4 – Paper Code 2022 linked, not harvested report
50 Model Unit Exploration 3.60 – Paper Code 2019 linked, not harvested report
51 Seq-to-seq attention 3.82 ✓ Paper Code 2018 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
52 CTC-CRF 4gram-LM 4.09 – Paper Code 2019 linked, not harvested report
53 HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations 4.3 – – – not matched report
54 Centaurus (30 M) 4.4 – Paper – 2025 no code linked report
55 HMM-TDNN + iVectors 4.8 ✓ – – not matched report
56 Gated ConvNets 4.8 – Paper Code 2017 linked, not harvested report
57 Deep Speech 2 5.33 – Paper Code 2015 community repositories only · 33 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 1 violated, 31 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified report
58 CTC + policy learning 5.42 – Paper – 2017 no code linked report
59 HMM-DNN + pNorm* 5.5 ✓ – – not matched report
60 Li-GRU 6.2 – Paper Code 2018 official (archive's flag): 2 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified report
61 Snips 6.4 – Paper Code 2018 official (archive's flag): 6 ran · 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified report
62 Local Prior Matching (Large Model) 7.19 – Paper Code 2020 linked, not harvested report
63 HMM-(SAT)GMM 8.0 ✓ – – not matched report
64 AmNet 8.6 – Paper – 2021 no code linked report

All 64 rows shown. 60 link to a paper page on this site; 24 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 18 rows have a graph line, from 15 distinct papers. Rows whose paper has a sample that ran: 18 (17 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument). Papers: 15 with a sample that ran: 14 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 18 rows with a graph line, 10 have an archive-official repository: on 5 a sample from it ran (4 with a run with no instrument failure), on 4 the samples that ran came from community repositories only, and on 1 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 216 samples: 167 ran (of which 12 constructed an object rather than computing a result; 137 with no instrument failure: 12 honoured, 9 violated, 116 with no contract checked; 30 where Syntology's instrument failed) · 49 unverified. Separately, 33 of those 216 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 25 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,587 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 18 proposed a result; of those 18, 18 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
HearInContext: A Benchmark for Implicit Context in Speech Recognition arXiv:2609.18680 16 Sep 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous... arXiv:2608.24168 25 Aug 2026 5 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction arXiv:2608.10878 11 Aug 2026 2 harvested: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result refused by a rule: the table reports a different split or setting than the leaderboard
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of... arXiv:2608.08638 9 Aug 2026 20 harvested: 13 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified refused by a rule: the table's column header does not name the leaderboard's metric
KVAE: Family of Tokenizers for Multimodal Generative Models arXiv:2608.05798 6 Aug 2026 2 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via... arXiv:2607.08117 9 Jul 2026 repository linked, no samples harvested refused by a rule: the row is an ablation variant, not the method itself
WavCube: Unifying Speech Representation for Understanding and Generation via... arXiv:2605.06407 7 May 2026 8 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Efficient Training for Cross-lingual Speech Language Models arXiv:2604.11096 13 Apr 2026 6 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
VoXtream2: Full-stream TTS with dynamic speaking rate control arXiv:2603.13518 13 Mar 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
Polynomial Mixing for Efficient Self-supervised Speech Encoders arXiv:2603.00683 28 Feb 2026 held, no recorded run refused by a rule: the table's column header does not name the leaderboard's metric
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization arXiv:2601.23174 30 Jan 2026 11 harvested: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic... arXiv:2601.16117 22 Jan 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts arXiv:2601.10272 15 Jan 2026 2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result refused by a rule: the table's column header does not name the leaderboard's metric
SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best... arXiv:2601.09385 14 Jan 2026 2 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step... arXiv:2512.23278 29 Dec 2025 7 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified refused by a rule: the table's column header does not name the leaderboard's metric
ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models arXiv:2510.26096 30 Oct 2025 12 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Latent Speech-Text Transformer arXiv:2510.06195 7 Oct 2025 18 harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified refused by a rule: the table's column header does not name the leaderboard's metric
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs arXiv:2509.22220 26 Sep 2025 5 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric

Syntology 18 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 18 counted above as giving no cell that passed the extractor's own checks are the 18 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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