Methods › General › Loss Functions › CTC Loss

Connectionist Temporal Classification Loss

CTC Loss

47 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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 ≤ the input length.

See Code · pytorch/pytorch

Papers archive 2025-07-28

30 shown of 47, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 42 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Speech Recognition24
speech-recognition23
Automatic Speech Recognition18
Automatic Speech Recognition (ASR)18
Language Modelling10
Language Modeling8
Decoder6
Knowledge Distillation4
Handwritten Text Recognition3
Lipreading3
Sign Language Recognition3
Translation3
Audio-Visual Speech Recognition2
CPU2
Data Augmentation2
GPU2
General Classification2
Multi-Task Learning2
Transfer Learning2
Visual Speech Recognition2

Usage over time archive 2025-07-28

Papers per year tagged with CTC Loss: 2016 to 2025, peak 9 9 0 2016: 1 paper 2016 2017: 2 papers 2017 2018: 4 papers 2018 2019: 4 papers 2019 2020: 5 papers 2020 2021: 9 papers 2021 2022: 9 papers 2022 2023: 6 papers 2023 2024: 6 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (47 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Loss Functions

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