Papers › Transformers with convolutional context for ASR

Transformers with convolutional context for ASR

26 Apr 2019arXiv:1904.11660archive 2025-07-28

Abdelrahman Mohamed, Dmytro Okhonko, Luke Zettlemoyer

The recent success of transformer networks for neural machine translation and other NLP tasks has led to a surge in research work trying to apply it for speech recognition. Recent efforts studied key research questions around ways of combining positional embedding with speech features, and stability of optimization for large scale learning of transformer networks. In this paper, we propose replacing the sinusoidal positional embedding for transformers with convolutionally learned input representations. These contextual representations provide subsequent transformer blocks with relative positional information needed for discovering long-range relationships between local concepts. The proposed system has favorable optimization characteristics where our reported results are produced with fixed learning rate of 1.0 and no warmup steps. The proposed model achieves a competitive 4.7% and 12.9% WER on the Librispeech ``test clean'' and ``test other'' subsets when no extra LM text is provided.

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

Syntology 8 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

George0828Zhang/simulst mentioned on GitHubpytorchSyntology: not harvested report
insop/pytorch-hackathon mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (1 instrument-failed) · 0 unverified report
sooftware/Fairseq-Listen-Attend-Spell mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Listen, Attend and Spell (arXiv:1508.01211; that paper's own run record: 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); nothing checks that they implement this paper's method. report
sooftware/OpenSpeech mentioned on GitHubpytorchMITSyntology: 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

8 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
7ran

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from insop/pytorch-hackathon. “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.

insop/pytorch-hackathon community (archive-listed) 8 samples, 8 ran (1 instrument-failed) · 0 unverified
add_asr_eval_argument in 6 papers asr-demo/infer_file.py ran Apache-2.0 (permissive) · 9d5ab7e22e729015 · report fixture: signature parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
calc_mean_invstddev asr-demo/infer_file.py ran fingerprinted Apache-2.0 (permissive) · 6114b8f553b73b81 · report fixture: signature feature:ndarray/2/float · returned tuple · level recorded 2026-09-24
compute_energy asr-demo/vad.py ran fingerprinted Apache-2.0 (permissive) · a0759a87ad6e2e61 · report fixture: signature frame:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_spectral_flatness asr-demo/vad.py ran fingerprinted Apache-2.0 (permissive) · d07f4e99c3cd187c · report fixture: signature frame:Tensor/1/float · returned Tensor · level recorded 2026-09-24
dataset_dest_prefix in 11 papers fairseq/preprocess.py ran Apache-2.0 (permissive) · 9eda7f80331d658c · report fixture: signature args:Args/0/?, output_prefix:str/0/str, lang:str/0/str · returned str · level recorded 2026-09-25
mono_to_color asr-demo/utils.py ran Apache-2.0 (permissive) · 1045ab840c0cd71a · report fixture: signature X:ndarray/2/float, mean:NoneType/0/?, std:NoneType/0/?, norm_max:NoneType/0/?, norm_min:NoneType/0/?, eps:float/0/float · returned ndarray · level recorded 2026-09-24
process_predictions asr-demo/infer_file.py ran Apache-2.0 (permissive) · 15c34dd848773d02 · report fixture: signature args:Args/0/?, hypos:list/1/dict, sp:SentencePieceProcessor/0/?, tgt_dict:TgtDict/0/? · returned list · level recorded 2026-09-24
safe_readline in 67 papers fairseq/fairseq/binarizer.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 82bdf940665aeeb4 · report fixture: signature f:StringIO/0/? · returned str · level recorded 2026-09-24

Tasks

Image ClassificationMachine TranslationSpeech RecognitionTranslationspeech-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 LayerReLUResidual 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