Automatic Restoration of Diacritics for Speech Data Sets

arXiv:2311.10771v2 Announce Type: replace
Abstract: Automatic text-based diacritic restoration models generally have high diacritic error rates when applied to speech transcripts as a result of domain and style shifts in spoken language. In this work, we explore the possibility of improving the performance of automatic diacritic restoration when applied to speech data by utilizing parallel spoken utterances. In particular, we use the pre-trained Whisper ASR model fine-tuned on relatively small amounts of diacritized Arabic speech data to produce rough diacritized …

abstract arxiv cs.cl cs.sd data data sets domain error explore improving language performance possibility speech spoken style text transcripts type work