Comparison Of Grapheme-to-Phoneme Conversions For Spoken Document Retrieval
Dmitriy Prozorov, Alexandra Tatarinova · 2019
The article contains analysis of spoken document retrieval techniques which apply word similarity based on phonemic transcriptions building or approximate string matching. Results are obtained on the collection of spoken documents with speech on Russian language. Grapheme-to-phoneme conversion methods based on a hidden Markov model and 1,2-order finite Markov chain is discussed on the article.