Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models.
Zhiyuan TangDong WangShen HuangShidong ShangPublished in: CoRR (2024)
Keyphrases
- error correction
- speech recognition
- language model
- chinese characters
- error tolerant
- language modeling
- character recognition
- n gram
- document retrieval
- retrieval model
- information retrieval
- probabilistic model
- speech signal
- test collection
- context sensitive
- handwriting recognition
- mixture model
- query expansion
- speaker identification
- automatic speech recognition
- word error rate
- query terms
- relevance model
- noisy environments
- word segmentation
- machine learning
- pairwise
- data mining