Browse State-of-the-Art › Speech Recognition
Speech Recognition
1,373 papers with code · 65 benchmarks · 96 datasets archive 2025-07-28
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.
( Image credit: SpecAugment )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
235 leaderboard tables shown for this task, 65 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 235 until expanded.
Syntology 23 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): LibriSpeech test-clean (18 judged, 0 placed), LibriSpeech test-other (8 judged, 0 placed), AISHELL-1 (3 judged, 0 placed), Speech Commands (2 judged, 0 placed), SPGISpeech (3 judged, 0 placed), AISHELL-2 (2 judged, 0 placed), Common Voice English (1 judged, 0 placed), TED-LIUM (3 judged, 0 placed), AISHELL-2 Test IOS (1 judged, 0 placed), GigaSpeech (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line 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”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
96 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 96 until expanded.
Subtasks archive 2025-07-28
11 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 6,433 · with a code link: 1,373 · where Syntology ran a sample: 196 (161 with a run with no instrument failure, 35 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (196 of 6,433 tagged: 161 with a run with no instrument failure, 35 where every run was a failure of Syntology's instrument)
Page 1 of 65: papers 1 to 100 of 6,433, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line 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”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
17 Feb 2016 41 repositories listed Syntology 47 ran (of which 17 constructed an object rather than computing a result; 27 with no instrument failure: 2 honoured, 0 violated, 25 with no contract checked; 20 where Syntology's instrument failed) · 30 unverified (of 77 harvested samples) · 50 pointer-only (licence)Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device.
-
5 Aug 2015 40 repositories listed Syntology 30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 10 where Syntology's instrument failed) · 21 unverified (of 51 harvested samples) · 9 pointer-only (licence)Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly.
-
9 Apr 2018 35 repositories listed Syntology 4 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; 4 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 1 pointer-only (licence)Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems.
-
8 Dec 2015 35 repositories listed Syntology 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 (of 39 harvested samples)We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages.
-
18 Apr 2019 30 repositories listed Syntology 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 (of 18 harvested samples)On LibriSpeech, we achieve 6.
-
20 Jun 2020 25 repositories listed Syntology 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 (of 9 harvested samples) · 2 pointer-only (licence)We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.
-
16 May 2020 25 repositories listed Syntology 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 (of 7 harvested samples) · 2 pointer-only (licence)Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
-
17 Dec 2014 24 repositories listed Syntology community repositories only · 9 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; 7 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 8 pointer-only (licence)We present a state-of-the-art speech recognition system developed using end-to-end deep learning.
-
8 Sep 2014 21 repositories listed Syntology community repositories only · 2 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; 2 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples) · 6 pointer-only (licence)We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units.
-
8 Mar 2021 19 repositories listed Syntology 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others.
-
13 Mar 2015 17 repositories listedSeveral variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995.
-
25 May 2018 16 repositories listed Syntology 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 (of 15 harvested samples)This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices.
-
6 Dec 2022 15 repositories listed Syntology community repositories only · 49 ran (of which 0 constructed an object rather than computing a result; 36 with no instrument failure: 4 honoured, 1 violated, 31 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified (of 59 harvested samples) · 21 pointer-only (licence)We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
-
8 May 2018 14 repositories listed Syntology 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 (of 12 harvested samples)Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition.
-
7 Oct 2016 14 repositories listed Syntology official (archive's flag): 12 ran · 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 4 honoured, 0 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 21 harvested samples) · 6 pointer-only (licence)We consider the two related problems of detecting if an example is misclassified or out-of-distribution.
-
24 Jun 2015 14 repositories listedRecurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image…
-
7 Feb 2022 12 repositories listed Syntology community repositories only · 4 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; 0 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind.
-
14 Jun 2021 11 repositories listed Syntology 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 (of 9 harvested samples)Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the…
-
19 Nov 2018 11 repositories listed Syntology 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 (of 6 harvested samples) · 6 pointer-only (licence)Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.
-
1 Apr 2021 10 repositories listed Syntology community repositories only · 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) · 2 unverified (of 16 harvested samples)The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition.
-
5 Apr 2019 10 repositories listedIn this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data.
-
26 Oct 2021 9 repositories listedSelf-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks.
-
11 Sep 2016 9 repositories listedThis paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding.
-
9 Jun 2015 9 repositories listed Syntology 4 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; 0 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples)Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning.
-
31 Oct 2021 8 repositories listed Syntology official (archive's flag): 5 ran · 37 ran (of which 8 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 1 violated, 18 with no contract checked; 16 where Syntology's instrument failed) · 18 unverified (of 55 harvested samples) · 3 pointer-only (licence)A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies.
-
24 Jun 2020 8 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages.
-
18 Dec 2018 8 repositories listedThis paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework.
-
21 Sep 2016 8 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 10 harvested samples)Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments.
-
25 Sep 2023 7 repositories listed Syntology official: harvested for another paper · 0 ran · 3 unverified (of 3 harvested samples)Pre-training speech models on large volumes of data has achieved remarkable success.
-
12 Jul 2020 7 repositories listed Syntology community repositories only · 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) · 3 unverified (of 14 harvested samples) · 3 pointer-only (licence)We present a large-scale comparison of various self-supervised models.
-
11 Apr 2019 7 repositories listed Syntology community repositories only · 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 (of 1 harvested sample)
-
14 Oct 2021 6 repositories listed Syntology community repositories only · 2 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; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
7 May 2020 6 repositories listed
-
5 Dec 2017 6 repositories listed
-
8 Jun 2017 6 repositories listed
-
3 Apr 2015 6 repositories listed
-
14 Dec 2022 5 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
12 Oct 2021 5 repositories listed
-
19 Jan 2021 5 repositories listed Syntology official (archive's flag): 1 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
10 Dec 2020 5 repositories listed
-
8 Nov 2020 5 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
11 Oct 2020 5 repositories listed
-
7 Feb 2020 5 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
-
3 Jan 2019 5 repositories listed
-
11 Oct 2018 5 repositories listed Syntology 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 (of 1 harvested sample) · 1 pointer-only (licence)
-
10 Sep 2017 5 repositories listed
-
22 Jun 2016 5 repositories listed Syntology community repositories only · 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 (of 2 harvested samples) · 2 pointer-only (licence)
-
12 Aug 2014 5 repositories listed
-
13 Jul 2024 4 repositories listed
-
22 May 2023 4 repositories listed Syntology community repositories only · 3 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; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
13 Apr 2023 4 repositories listed Syntology community repositories only · 1 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; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
4 Nov 2022 4 repositories listed
-
12 Oct 2022 4 repositories listed Syntology community repositories only · 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) · 1 unverified (of 2 harvested samples)
-
2 Jun 2022 4 repositories listed Syntology 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 (of 49 harvested samples)
-
3 Feb 2022 4 repositories listed Syntology 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 4 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 3 pointer-only (licence)
-
7 Aug 2021 4 repositories listed
-
24 May 2021 4 repositories listed Syntology community repositories only · 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 (of 1 harvested sample) · 1 pointer-only (licence)
-
13 Mar 2021 4 repositories listed
-
2 Feb 2021 4 repositories listed
-
9 Nov 2019 4 repositories listed
-
6 Jun 2019 4 repositories listed Syntology 6 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; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 2 pointer-only (licence)
-
26 Apr 2019 4 repositories listed Syntology 8 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; 1 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 1 pointer-only (licence)
-
30 Oct 2018 4 repositories listed
-
6 Sep 2018 4 repositories listed
-
31 Aug 2018 4 repositories listed
-
15 Feb 2018 4 repositories listed
-
5 Dec 2017 4 repositories listed
-
5 Dec 2017 4 repositories listed
-
18 Oct 2017 4 repositories listed
-
12 Mar 2017 4 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
-
25 Nov 2016 4 repositories listed Syntology 2 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; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
29 Jul 2015 4 repositories listed
-
23 Jul 2015 4 repositories listed Syntology official (archive's flag): 8 ran · 13 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; 0 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples)
-
14 Oct 2014 4 repositories listed
-
17 Sep 2024 3 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
4 Jul 2024 3 repositories listed Syntology official (archive's flag): 9 ran · 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples)
-
13 Feb 2024 3 repositories listed
-
7 Nov 2023 3 repositories listed
-
18 Jun 2023 3 repositories listed
-
8 Nov 2022 3 repositories listed
-
6 Jul 2022 3 repositories listed
-
29 Mar 2022 3 repositories listed
-
29 Mar 2022 3 repositories listed Syntology community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 9 pointer-only (licence)
-
1 Feb 2022 3 repositories listed
-
4 Nov 2021 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 6 unverified (of 6 harvested samples)
-
15 Oct 2021 3 repositories listed
-
7 Oct 2021 3 repositories listed
-
15 Jun 2021 3 repositories listed
-
13 Jun 2021 3 repositories listed Syntology official (archive's flag): 1 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 1 pointer-only (licence)
-
12 Feb 2021 3 repositories listed
-
22 Oct 2020 3 repositories listed
-
6 Oct 2020 3 repositories listed
-
1 Oct 2020 3 repositories listed
-
7 Sep 2020 3 repositories listed
Syntology lines on 54 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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