Papers › CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition

CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition

17 Jul 2020arXiv:2007.09127links table onlyarchive 2025-07-28

Ludwig Kürzinger, Dominik Winkelbauer, Lujun Li, Tobias Watzel, Gerhard Rigoll

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance. In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over 1700h of speech data. For data preparation, we propose a two-stage approach that uses an ASR model pre-trained with Connectionist Temporal Classification (CTC) to boot-strap more training data from unsegmented or unlabeled training data. Utterances are then extracted from label probabilities obtained from the network trained with CTC to determine segment alignments. With this training data, we trained a hybrid CTC/attention Transformer model that achieves 12.8% WER on the Tuda-DE test set, surpassing the previous baseline of 14.4% of conventional hybrid DNN/HMM ASR.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2007.09127")

Code

Syntology Ran 3 of 10 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 7 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cornerfarmer/ctc_segmentation officialmentioned in papermentioned on GitHubApache-2.0 report
danoneata/espnet mentioned on GitHubpytorchApache-2.0 report
jumon/espnet-1 mentioned on GitHubpytorchApache-2.0 report
jzmo/espnet mentioned on GitHubpytorchApache-2.0 report
lumaku/ctc-segmentation mentioned on GitHubpytorchApache-2.0 report
lumaku/german-corpus-aligned mentioned on GitHub report
pzelasko/espnet mentioned on GitHubpytorchApache-2.0 report
victor45664/espnet mentioned on GitHubpytorchApache-2.0 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

10 samples harvested; 3 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

3ran
7unverified

Licence: 0 of the 10 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; each sample names its own and says which. “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.

prepare_text cornerfarmer/ctc_segmentation/align.py official repository unverified Apache-2.0 (permissive) · 4122d89455a8def4 · report
recognize cornerfarmer/ctc_segmentation/decode.py official repository unverified Apache-2.0 (permissive) · d4a13bf0db9e2d8f · report
write_output cornerfarmer/ctc_segmentation/align.py official repository unverified Apache-2.0 (permissive) · 8fd1afbcfc039bd4 · report
get_partitions lumaku/ctc-segmentation/ctc_segmentation/partitioning.py community (archive-listed) ran Apache-2.0 (permissive) · 05b5b68ce0fb9aa0 · report
prepare_text lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py community (archive-listed) ran Apache-2.0 (permissive) · a99ea16d4a737423 · report
prepare_tokenized_text lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py community (archive-listed) ran Apache-2.0 (permissive) · 2073edbaac1f78f1 · report
adadelta_eps_decay danoneata/espnet/espnet/asr/asr_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · bb3665ddb6b8dd2d · report
adam_lr_decay danoneata/espnet/espnet/asr/asr_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 1fa5ca494ed9750a · report
ctc_segmentation lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py community (archive-listed) unverified Apache-2.0 (permissive) · 97301ff4a47ba9d9 · report
restore_snapshot danoneata/espnet/espnet/asr/asr_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 96081a60369c59e0 · report

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition TUDA Hybrid CTC/Attention Test WER 12.8% #5 of 9 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