KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing.
Seonmin KooChanjun ParkJinsung KimJaehyung SeoSugyeong EoHyeonseok MoonHeuiseok LimPublished in: EMNLP (2023)
Keyphrases
- post processing
- benchmark datasets
- preprocessing
- automatic speech recognition
- pedestrian detection
- error rate
- post processed
- projections onto convex sets
- speech recognition
- pattern extraction
- filtering method
- classification algorithm
- shape error concealment
- coded images
- feature selection
- knowledge acquisition
- domain specific
- decision trees