Iterative Pseudo-Labeling (IPL) is a semi-supervised algorithm for speech recognition which efficiently performs multiple iterations of pseudo-labeling on unlabeled data as the acoustic model evolves. In particular, IPL fine tunes an existing model at each iteration using both labeled data and a subset of unlabeled data.
Source: Iterative Pseudo-Labeling for Speech RecognitionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Automatic Speech Recognition (ASR) | 2 | 11.11% |
Language Modelling | 2 | 11.11% |
Speech Recognition | 2 | 11.11% |
Computational Efficiency | 1 | 5.56% |
Collaborative Filtering | 1 | 5.56% |
Recommendation Systems | 1 | 5.56% |
Image Generation | 1 | 5.56% |
Image Segmentation | 1 | 5.56% |
Medical Image Segmentation | 1 | 5.56% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |