Semi-Supervised Learning Methods
Iterative Pseudo-Labeling
Introduced by Xu et al. in Iterative Pseudo-Labeling for Speech RecognitionIterative 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 Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Automatic Speech Recognition (ASR) | 2 | 7.14% |
| Language Modeling | 2 | 7.14% |
| Language Modelling | 2 | 7.14% |
| Speech Recognition | 2 | 7.14% |
| RAG | 1 | 3.57% |
| Prompt Engineering | 1 | 3.57% |
| Speaker Recognition | 1 | 3.57% |
| Speaker Verification | 1 | 3.57% |
| Computational Efficiency | 1 | 3.57% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
