Showing cs.CLShow all
2 papers · 1 filter
cs.CL2023
PATCorrect: Non-autoregressive Phoneme-augmented Transformer for ASR Error Correction
Ziji Zhang, Zhehui Wang, Rajesh Kamma +2
Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have…
cs.CL2021
Search and Learn: Improving Semantic Coverage for Data-to-Text Generation
Shailza Jolly, Zi Xuan Zhang, Andreas Dengel +1
Data-to-text generation systems aim to generate text descriptions based on input data (often represented in the tabular form). A typical system uses huge training samples for learn…