{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ctc-loss","slug":"ctc-loss","name":"CTC Loss","full_name":"Connectionist Temporal Classification Loss","full_name_withheld":false,"description_markdown":"A **Connectionist Temporal Classification Loss**, or **CTC Loss**, is designed for tasks where we need alignment between sequences, but where that alignment is difficult - e.g. aligning each character to its location in an audio file. It calculates a loss between a continuous (unsegmented) time series and a target sequence. It does this by summing over the probability of possible alignments of input to target, producing a loss value which is differentiable with respect to each input node. The alignment of input to target is assumed to be “many-to-one”, which limits the length of the target sequence such that it must be $\\leq$ the input length.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":"https://github.com/pytorch/pytorch/blob/8850fd1952c3983793dcac4022fdc8e3913dad96/torch/nn/modules/loss.py#L1247","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":47,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"analyzing-the-importance-of-blank-for-ctc","title":"Analyzing the Importance of Blank for CTC-Based Knowledge Distillation","date":"2025-06-02","arxiv_id":"2506.01503","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-canonical-neural-units-and-multi","title":"Integrating Canonical Neural Units and Multi-Scale Training for Handwritten Text Recognition","date":"2024-10-24","arxiv_id":"2410.18374","n_code_links":0,"syntology":null},{"paper":null,"slug":"serialized-speech-information-guidance-with","title":"Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition","date":"2024-09-01","arxiv_id":"2409.00815","n_code_links":0,"syntology":null},{"paper":"/paper/li-tta-language-informed-test-time-adaptation","slug":"li-tta-language-informed-test-time-adaptation","title":"LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition","date":"2024-08-11","arxiv_id":"2408.05769","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-robustness-of-llm-based-speech","title":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment","date":"2024-06-25","arxiv_id":"2406.17957","n_code_links":0,"syntology":null},{"paper":"/paper/best-practices-for-a-handwritten-text","slug":"best-practices-for-a-handwritten-text","title":"Best Practices for a Handwritten Text Recognition System","date":"2024-04-17","arxiv_id":"2404.11339","n_code_links":1,"syntology":null},{"paper":null,"slug":"adamer-ctc-connectionist-temporal","title":"AdaMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition","date":"2024-03-18","arxiv_id":"2403.11578","n_code_links":0,"syntology":null},{"paper":"/paper/key-frame-mechanism-for-efficient-conformer","slug":"key-frame-mechanism-for-efficient-conformer","title":"Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognition","date":"2023-10-23","arxiv_id":"2310.14954","n_code_links":1,"syntology":null},{"paper":"/paper/self-distillation-regularized-connectionist","slug":"self-distillation-regularized-connectionist","title":"Self-distillation Regularized Connectionist Temporal Classification Loss for Text Recognition: A Simple Yet Effective Approach","date":"2023-08-17","arxiv_id":"2308.08806","n_code_links":1,"syntology":null},{"paper":null,"slug":"alternative-pseudo-labeling-for-semi","title":"Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition","date":"2023-08-12","arxiv_id":"2308.06547","n_code_links":0,"syntology":null},{"paper":null,"slug":"align-with-purpose-optimize-desired","title":"Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework","date":"2023-07-04","arxiv_id":"2307.01715","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-non-autoregressive-translation-1","title":"Improving Non-autoregressive Translation Quality with Pretrained Language Model, Embedding Distillation and Upsampling Strategy for CTC","date":"2023-06-10","arxiv_id":"2306.06345","n_code_links":0,"syntology":null},{"paper":null,"slug":"intapt-information-theoretic-adversarial","title":"INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition","date":"2023-05-25","arxiv_id":"2305.16371","n_code_links":0,"syntology":null},{"paper":"/paper/softcorrect-error-correction-with-soft","slug":"softcorrect-error-correction-with-soft","title":"SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition","date":"2022-12-02","arxiv_id":"2212.01039","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/NeuralSpeech"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/weakly-supervised-fingerspelling-recognition","slug":"weakly-supervised-fingerspelling-recognition","title":"Weakly-supervised Fingerspelling Recognition in British Sign Language Videos","date":"2022-11-16","arxiv_id":"2211.08954","n_code_links":1,"syntology":null},{"paper":null,"slug":"peak-first-ctc-reducing-the-peak-latency-of","title":"Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization","date":"2022-11-07","arxiv_id":"2211.03284","n_code_links":0,"syntology":null},{"paper":"/paper/temporal-superimposed-crossover-module-for","slug":"temporal-superimposed-crossover-module-for","title":"Temporal superimposed crossover module for effective continuous sign language","date":"2022-11-07","arxiv_id":"2211.03387","n_code_links":1,"syntology":null},{"paper":"/paper/trimtail-low-latency-streaming-asr-with","slug":"trimtail-low-latency-streaming-asr-with","title":"TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty","date":"2022-11-01","arxiv_id":"2211.00522","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"uconv-conformer-high-reduction-of-input","title":"Uconv-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition","date":"2022-08-16","arxiv_id":"2208.07657","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-acoustic-contextual-representation","title":"Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR","date":"2022-07-03","arxiv_id":"2207.01039","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-temporal-network-for-continuous","title":"Multi-scale temporal network for continuous sign language recognition","date":"2022-04-08","arxiv_id":"2204.03864","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-autoregressive-asr-with-self-conditioned","title":"Non-Autoregressive ASR with Self-Conditioned Folded Encoders","date":"2022-02-17","arxiv_id":"2202.08474","n_code_links":0,"syntology":null},{"paper":null,"slug":"pm-mmut-boosted-phone-mask-data-augmentation","title":"PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition","date":"2021-12-13","arxiv_id":"2112.06721","n_code_links":0,"syntology":null},{"paper":"/paper/fast-md-fast-multi-decoder-end-to-end-speech","slug":"fast-md-fast-multi-decoder-end-to-end-speech","title":"Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates","date":"2021-09-27","arxiv_id":"2109.12804","n_code_links":1,"syntology":null},{"paper":"/paper/golos-russian-dataset-for-speech-research","slug":"golos-russian-dataset-for-speech-research","title":"Golos: Russian Dataset for Speech Research","date":"2021-06-18","arxiv_id":"2106.10161","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sberdevices/golos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/multi-speaker-asr-combining-non","slug":"multi-speaker-asr-combining-non","title":"Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain","date":"2021-06-16","arxiv_id":"2106.08595","n_code_links":1,"syntology":null},{"paper":"/paper/why-does-ctc-result-in-peaky-behavior","slug":"why-does-ctc-result-in-peaky-behavior","title":"Why does CTC result in peaky behavior?","date":"2021-05-31","arxiv_id":"2105.14849","n_code_links":1,"syntology":null},{"paper":null,"slug":"relaxing-the-conditional-independence","title":"Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions","date":"2021-04-06","arxiv_id":"2104.02724","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiple-hypothesis-ctc-based-semi-supervised","title":"Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition","date":"2021-03-29","arxiv_id":"2103.15515","n_code_links":0,"syntology":null},{"paper":null,"slug":"intermediate-loss-regularization-for-ctc","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","date":"2021-02-05","arxiv_id":"2102.03216","n_code_links":0,"syntology":null},{"paper":"/paper/self-mutual-distillation-learning-for","slug":"self-mutual-distillation-learning-for","title":"Self-Mutual Distillation Learning for Continuous Sign Language Recognition","date":"2021-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/recurrence-free-unconstrained-handwritten","slug":"recurrence-free-unconstrained-handwritten","title":"Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network","date":"2020-12-09","arxiv_id":"2012.04961","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-transformer-ctc-networks-for-hardware","title":"Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering","date":"2020-08-05","arxiv_id":"2008.02323","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-frequency-lstm-an-efficient","title":"Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition","date":"2020-06-30","arxiv_id":"2007.00131","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-speech-translation-with-knowledge-1","title":"End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020","date":"2020-06-04","arxiv_id":"2006.02965","n_code_links":0,"syntology":null},{"paper":null,"slug":"reducing-spelling-inconsistencies-in-code","title":"Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss","date":"2020-05-16","arxiv_id":"2005.07920","n_code_links":0,"syntology":null},{"paper":null,"slug":"lipreading-with-3d-2d-cnn-blstm-hmm-and-word","title":"LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models","date":"2019-06-25","arxiv_id":"1906.12170","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-re-weighting-method-for-connectionist","slug":"a-novel-re-weighting-method-for-connectionist","title":"Reinterpreting CTC training as iterative fitting","date":"2019-04-24","arxiv_id":"1904.10619","n_code_links":2,"syntology":null},{"paper":"/paper/adversarial-generation-of-handwritten-text","slug":"adversarial-generation-of-handwritten-text","title":"Adversarial Generation of Handwritten Text Images Conditioned on Sequences","date":"2019-03-01","arxiv_id":"1903.00277","n_code_links":1,"syntology":null},{"paper":"/paper/ctcmodel-a-keras-model-for-connectionist","slug":"ctcmodel-a-keras-model-for-connectionist","title":"CTCModel: a Keras Model for Connectionist Temporal Classification","date":"2019-01-23","arxiv_id":"1901.07957","n_code_links":5,"syntology":null},{"paper":"/paper/accurate-data-efficient-unconstrained-text","slug":"accurate-data-efficient-unconstrained-text","title":"Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks","date":"2018-12-31","arxiv_id":"1812.11894","n_code_links":1,"syntology":null},{"paper":"/paper/audio-visual-speech-recognition-with-a-hybrid","slug":"audio-visual-speech-recognition-with-a-hybrid","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","date":"2018-09-28","arxiv_id":"1810.00108","n_code_links":0,"syntology":null},{"paper":"/paper/deep-audio-visual-speech-recognition","slug":"deep-audio-visual-speech-recognition","title":"Deep Audio-Visual Speech Recognition","date":"2018-09-06","arxiv_id":"1809.02108","n_code_links":4,"syntology":null},{"paper":"/paper/improved-training-of-end-to-end-attention","slug":"improved-training-of-end-to-end-attention","title":"Improved training of end-to-end attention models for speech recognition","date":"2018-05-08","arxiv_id":"1805.03294","n_code_links":14,"syntology":{"ran":12,"of":12,"n_ran_checked":12,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"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","official":null}},{"paper":null,"slug":"comparison-of-decoding-strategies-for-ctc","title":"Comparison of Decoding Strategies for CTC Acoustic Models","date":"2017-08-15","arxiv_id":"1708.04469","n_code_links":0,"syntology":null},{"paper":"/paper/emotion-recognition-from-speech-with","slug":"emotion-recognition-from-speech-with","title":"Emotion Recognition From Speech With Recurrent Neural Networks","date":"2017-01-27","arxiv_id":"1701.08071","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-speech-recognizer-acoustic-to-word","title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","date":"2016-10-31","arxiv_id":"1610.09975","n_code_links":0,"syntology":null}],"papers_shown":47,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":47,"with_a_code_link":21,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":47,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/method/ctc-loss/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/ctc-loss/papers/ran/1","json":"/method/ctc-loss/papers/ran/1.json","rows":4}],"tasks":[{"task":"/task/speech-recognition","name":"Speech Recognition","papers":24},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":23},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":18},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":18},{"task":"/task/language-modelling","name":"Language Modelling","papers":10},{"task":"/task/language-modeling","name":"Language Modeling","papers":8},{"task":"/task/decoder","name":"Decoder","papers":6},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":4},{"task":"/task/handwritten-text-recognition","name":"Handwritten Text Recognition","papers":3},{"task":"/task/lipreading","name":"Lipreading","papers":3},{"task":"/task/sign-language-recognition","name":"Sign Language Recognition","papers":3},{"task":"/task/translation","name":"Translation","papers":3},{"task":"/task/audio-visual-speech-recognition","name":"Audio-Visual Speech Recognition","papers":2},{"task":null,"name":"CPU","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":null,"name":"GPU","papers":2},{"task":"/task/classification","name":"General Classification","papers":2},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/visual-speech-recognition","name":"Visual Speech Recognition","papers":2}],"tasks_shown":20,"n_tasks":42,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":2},{"year":"2018","papers":4},{"year":"2019","papers":4},{"year":"2020","papers":5},{"year":"2021","papers":9},{"year":"2022","papers":9},{"year":"2023","papers":6},{"year":"2024","papers":6},{"year":"2025","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ctc-loss"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=CTC%20Loss","read_at":"2026-10-05T00:54:20+00:00","query":"CTC Loss","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'CTC Loss' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["CR-CTC","CTC-DID","MOE-CTC","OWSM-CTC","Granite 5.0 Turbo CTC","Constrained CTC Decoding","CTC-guided Modality Adapter","contrastive temporal coding (CTC)"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"cc9dfac1b580e6f3abf8f28c56f73320e41b8ea56cafacff794d5514d712371b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}