{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ctc-segmentation-of-large-corpora-for-german","title":"CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition","arxiv_id":"2007.09127","date":"2020-07-17","proceeding":null,"authors":["Ludwig Kürzinger","Dominik Winkelbauer","Lujun Li","Tobias Watzel","Gerhard Rigoll"],"abstract":"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 $1700$h 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.","url_abs":"https://arxiv.org/abs/2007.09127v1","url_pdf":"https://arxiv.org/pdf/2007.09127v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/cornerfarmer/ctc_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/EsamGhaleb/SharedLinguisticConstructions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/danoneata/espnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/jumon/espnet-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/jzmo/espnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/lumaku/ctc-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/lumaku/german-corpus-aligned","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/pzelasko/espnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/victor45664/espnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/warpctc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/Mind23-2/MindCode-2/tree/main/warpctc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"ctc-segmentation-of-large-corpora-for-german","repo_url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/wave_mlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-tuda","task":"Speech Recognition","dataset":"TUDA","model":"Hybrid CTC/Attention","rank_in_archive_order":5,"of":9,"metrics":{"Test WER":"12.8%"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.09127","atlas_url":"https://app.syntology.ai/?focus=2007.09127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09127"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/warpctc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pzelasko/espnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-2/tree/main/warpctc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jumon/espnet-1","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cornerfarmer/ctc_segmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lumaku/german-corpus-aligned","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/danoneata/espnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/wave_mlp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EsamGhaleb/SharedLinguisticConstructions","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lumaku/ctc-segmentation","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jzmo/espnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/victor45664/espnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":7},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1},"listed":{"samples":7,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"05b5b68ce0fb9aa0","entry":"get_partitions","repo":"lumaku/ctc-segmentation","repo_kind":"listed","path":"ctc_segmentation/partitioning.py","file_url":"https://github.com/lumaku/ctc-segmentation/blob/HEAD/ctc_segmentation/partitioning.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05b5b68ce0fb9aa0"}},{"code_sha256_prefix":"a99ea16d4a737423","entry":"prepare_text","repo":"lumaku/ctc-segmentation","repo_kind":"listed","path":"ctc_segmentation/ctc_segmentation.py","file_url":"https://github.com/lumaku/ctc-segmentation/blob/HEAD/ctc_segmentation/ctc_segmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a99ea16d4a737423"}},{"code_sha256_prefix":"2073edbaac1f78f1","entry":"prepare_tokenized_text","repo":"lumaku/ctc-segmentation","repo_kind":"listed","path":"ctc_segmentation/ctc_segmentation.py","file_url":"https://github.com/lumaku/ctc-segmentation/blob/HEAD/ctc_segmentation/ctc_segmentation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2073edbaac1f78f1"}},{"code_sha256_prefix":"bb3665ddb6b8dd2d","entry":"adadelta_eps_decay","repo":"danoneata/espnet","repo_kind":"listed","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/danoneata/espnet/blob/HEAD/espnet/asr/asr_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb3665ddb6b8dd2d"}},{"code_sha256_prefix":"1fa5ca494ed9750a","entry":"adam_lr_decay","repo":"danoneata/espnet","repo_kind":"listed","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/danoneata/espnet/blob/HEAD/espnet/asr/asr_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fa5ca494ed9750a"}},{"code_sha256_prefix":"97301ff4a47ba9d9","entry":"ctc_segmentation","repo":"lumaku/ctc-segmentation","repo_kind":"listed","path":"ctc_segmentation/ctc_segmentation.py","file_url":"https://github.com/lumaku/ctc-segmentation/blob/HEAD/ctc_segmentation/ctc_segmentation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"97301ff4a47ba9d9"}},{"code_sha256_prefix":"4122d89455a8def4","entry":"prepare_text","repo":"cornerfarmer/ctc_segmentation","repo_kind":"official","path":"align.py","file_url":"https://github.com/cornerfarmer/ctc_segmentation/blob/HEAD/align.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4122d89455a8def4"}},{"code_sha256_prefix":"d4a13bf0db9e2d8f","entry":"recognize","repo":"cornerfarmer/ctc_segmentation","repo_kind":"official","path":"decode.py","file_url":"https://github.com/cornerfarmer/ctc_segmentation/blob/HEAD/decode.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4a13bf0db9e2d8f"}},{"code_sha256_prefix":"96081a60369c59e0","entry":"restore_snapshot","repo":"danoneata/espnet","repo_kind":"listed","path":"espnet/asr/asr_utils.py","file_url":"https://github.com/danoneata/espnet/blob/HEAD/espnet/asr/asr_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96081a60369c59e0"}},{"code_sha256_prefix":"8fd1afbcfc039bd4","entry":"write_output","repo":"cornerfarmer/ctc_segmentation","repo_kind":"official","path":"align.py","file_url":"https://github.com/cornerfarmer/ctc_segmentation/blob/HEAD/align.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fd1afbcfc039bd4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}