← Search

Linchen Zhu

2 accepted papers

2021

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition

EMNLP 2021finding

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one se…

2021

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

NeurIPS 2021poster

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR outputs. Previous works usually use a sequence-to-sequence model to correct an ASR output sentence autoregressively, wh…