Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data.
Mozhdeh GheiniTatiana LikhomanenkoMatthias SperberHendra SetiawanPublished in: CoRR (2022)
Keyphrases
- data sets
- data analysis
- data distribution
- database
- image data
- probability distribution
- data collection
- data points
- dimensionality reduction
- original data
- spatial data
- feature space
- high quality
- complex data
- data quality
- website
- databases
- statistical analysis
- raw data
- experimental data
- missing data
- uniformly distributed
- historical data
- noisy data
- data acquisition
- social networks
- feature selection
- prior knowledge
- high dimensional data
- unsupervised learning
- computer systems
- training data
- small number
- data structure
- end users