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.
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Recognition | 21 | 29.17% |
Automatic Speech Recognition (ASR) | 16 | 22.22% |
Language Modelling | 8 | 11.11% |
Translation | 3 | 4.17% |
Sign Language Recognition | 3 | 4.17% |
Lipreading | 3 | 4.17% |
Multi-Task Learning | 2 | 2.78% |
General Classification | 2 | 2.78% |
Audio-Visual Speech Recognition | 2 | 2.78% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |