Papers › Deep Speech: Scaling up end-to-end speech recognition

Deep Speech: Scaling up end-to-end speech recognition

17 Dec 2014arXiv:1412.5567archive 2025-07-28

Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, Andrew Y. Ng

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.

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

No sample from the archive's official repository (PaddlePaddle/PaddleSpeech) is linked to this paper; the 9 samples below come from 3 community repositories. Syntology harvested code from PaddlePaddle/PaddleSpeech for another paper.

PaddlePaddle/PaddleSpeech: Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 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) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 9 code samples harvested from 3 repositories linked to this paper: 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. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 3 repositories, 9 ran (2 with no instrument failure; 7 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 4 of its repositories that Syntology harvested for other papers:

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

24 repositories listed; official and paper-mentioned ones first.

PaddlePaddle/PaddleSpeech officialpaddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 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) · 5 unverified); nothing checks that they implement this paper's method. report
CorrelAid/codingchallenge1020_team1 mentioned on GitHubtfSyntology: not harvested report
Digital-Umuganda/Deepspeech-Kinyarwanda mentioned on GitHubtfMPL-2.0Syntology: not harvested report
GeorgeFedoseev/DeepSpeech mentioned on GitHubtfSyntology: not harvested report
IBM/MAX-Speech-to-Text-Converter mentioned on GitHubtfApache-2.0Syntology: not harvested report
Loghijiaha/DeepSpeech-Indo mentioned on GitHubtfMPL-2.0Syntology: not harvested report
Picovoice/speech-to-text-benchmark mentioned on GitHubApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization... (arXiv:2310.02943; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
Picovoice/stt-benchmark mentioned on GitHubApache-2.0Syntology: not harvested report
RashadGarayev/TRSpeech-to-text mentioned on GitHubtfSyntology: not harvested report
RezisEwig/unity_speech mentioned on GitHubSyntology: not harvested report
WalterJohnson0/DeepSpeech-KerasRebuild mentioned on GitHubtfMITSyntology: not harvested report
YuBeomGon/DeepSpeech mentioned on GitHubtfSyntology: 6 samples, 6 ran (5 instrument-failed) · 0 unverified report
anssssss/Vietnamese-Speech-Recognition mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
bjtommychen/Keras_DeepSpeech2_SpeechRecognition mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Speech 2: End-to-End Speech Recognition in English and Mandarin (arXiv:1512.02595; that paper's own run record: 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); nothing checks that they implement this paper's method. report
lissyx/STT mentioned on GitHubtfMPL-2.0Syntology: not harvested report
mangushev/deep_speech mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
mozilla/DeepSpeech mentioned on GitHubtfMPL-2.0Syntology: not harvested report
mozilla/STT mentioned on GitHubtfMPL-2.0Syntology: not harvested report
msalhab96/SpeeQ mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Squeezeformer: An Efficient Transformer for Automatic Speech Recognition (arXiv:2206.00888; that paper's own run record: 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); nothing checks that they implement this paper's method. report
myrtleSoftware/deepspeech mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
pannous/caffe-speech-recognition mentioned on GitHubcaffe2Syntology: not harvested report
robmsmt/KerasDeepSpeech mentioned on GitHubtfAGPL-3.0Syntology: not harvested report
soarsmu/crossasr mentioned on GitHubpaddleSyntology: not harvested report
tuanio/deepspeech-ctc pytorchSyntology: not harvested 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

9 samples harvested: 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. “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.

2ran · honoured contract
5ran · our draft was wrong
2ran; the contract check could not run

Licence: 8 of the 9 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

YuBeomGon/DeepSpeech community (archive-listed) 6 samples, 6 ran (5 instrument-failed) · 0 unverified
get_audio_format util/audio.py ran · honoured contract no licence file found · pointer only · 51944d6733966676 · report fixture: signature wav_file:MockWavFile/0/? · returned tuple · level recorded 2026-09-22
get_duration in 6 papers util/audio.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 1cb244d6be841554 · report fixture: signature audio_data:bytes/0/?, audio_format:tuple/1/int · returned float · level recorded 2026-09-22
get_num_samples util/audio.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 50176dcc6ddee70e · report fixture: signature audio_data:bytes/0/?, audio_format:tuple/1/int · returned int · level recorded 2026-09-22
resolve in 15 papers transcribe.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3306aa443c436614 · report fixture: signature base_path:str/0/str, spec_path:str/0/str · returned str · level recorded 2026-09-22
sparse_tensor_value_to_texts evaluate.py ran · our draft was wrong no licence file found · pointer only · fb9b291fc581e945 · report fixture: signature value:MockSparseTensor/0/?, alphabet:MockAlphabet/0/? · returned list · level recorded 2026-09-22
sparse_tuple_to_texts evaluate.py ran · our draft was wrong no licence file found · pointer only · 970f4ac6b4021aaf · report fixture: signature sp_tuple:tuple/1/list, alphabet:SimpleAlphabet/0/? · returned list · level recorded 2026-09-22
anssssss/Vietnamese-Speech-Recognition community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
out src/evaluate.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7c01db5a56271dd6 · report fixture: signature list:list/1/str · returned list · level recorded 2026-09-22
process in 60 papers src/model.py ran · honoured contract no licence file found · pointer only · 232015401802af14 · report fixture: signature file:StringIO/0/? · returned list · level recorded 2026-09-22
mangushev/deep_speech community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
read_labels in 11 papers prepare_libri.py ran · our draft was wrong MIT (permissive) · a7e204ec063f026b · report fixture: signature label_file:str/0/str · returned dict · level recorded 2026-09-22

Tasks

Accented Speech RecognitionSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Accented Speech Recognition VoxForge American-Canadian Deep Speech Percentage error 15.01 #2 of 2 Archive leaderboard report
Accented Speech Recognition VoxForge Commonwealth Deep Speech Percentage error 28.46 #2 of 2 Archive leaderboard report
Accented Speech Recognition VoxForge European Deep Speech Percentage error 31.20 #2 of 2 Archive leaderboard report
Accented Speech Recognition VoxForge Indian Deep Speech Percentage error 45.35 #2 of 2 Archive leaderboard report
Noisy Speech Recognition CHiME clean CNN + Bi-RNN + CTC (speech to letters) Percentage error 6.3 #2 of 2 Archive leaderboard report
Noisy Speech Recognition CHiME real CNN + Bi-RNN + CTC (speech to letters) Percentage error 67.94 #5 of 5 Archive leaderboard report
Speech Recognition Switchboard + Hub500 Deep Speech + FSH Percentage error 12.6 #20 of 30 Archive leaderboard report
Speech Recognition Switchboard + Hub500 CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB Percentage error 12.6 #21 of 30 Archive leaderboard report
Speech Recognition Switchboard + Hub500 Deep Speech Percentage error 20 #30 of 30 Archive leaderboard report
Speech Recognition swb_hub_500 WER fullSWBCH CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWB Percentage error 16 #8 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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