We present software that, in only a few hours, transcribes forty hours of recorded speech in a surprise language, using only a few tens of megabytes of noisy text in that language, and a zero-resource grapheme to phoneme (G2P) table. A pretrained acoustic model maps acoustic features to phonemes; a reversed G2P maps these to graphemes; then a language model maps these to a most-likely grapheme sequence, i.e., a transcription. This software has worked successfully with corpora in Arabic, Assam, Kinyarwanda, Russian, Sinhalese, Swahili, Tagalog, and Tamil.
@article{arxiv.1909.07285,
title = {Fast transcription of speech in low-resource languages},
author = {Mark Hasegawa-Johnson and Camille Goudeseune and Gina-Anne Levow},
journal= {arXiv preprint arXiv:1909.07285},
year = {2019}
}