Automatic speech recognition (ASR) technologies enable humans to communicate with computers. Isolated word recognition (IWR) is an important part of many known ASR systems. Minimizing the word error rate in cases of incremental learning is a unique challenge for developing an on-line ASR system. This paper focuses on on-line IWR using a recursive hidden Markov model (HMM) multivariate parameter estimation algorithm. The maximum likelihood method was used to estimate the unknown parameters of the model, and an algorithm for the adapted recursive EM algorithm for HMMs parameter estimation was derived. The resulting recursive EM algorithm is unique among its counterparts because of state transition probabilities calculation. It obtains more accurate parameter estimates compared to other algorithms of this type. In our experiment, the algorithm was implemented and adapted to several datasets for IWR. Thus, the recognition rate and algorithm convergence results are discussed in this work.
Šiame darbe apžvelgti automatinio šnekos atpažinimo metodai. Paslėptųjų Markovo modelių metodu apmokyti akustiniai modeliai, sukurtas kalbos modelis ir žodynas. Akustiniai modeliai apmokyti žinių įrašais, kurių trukmė siekia 2 valandas ir 20 minučių, o žodyno apimtis – 5 859 žodžius. Eksperimentams naudotos dvi fonetinės sistemos, kuriose yra 85 ir 32 fonemos, sudarytos remiantis lietuvių kalbos tarties žodynu. Sukurti modeliai integruoti į stenografavimo įrankio prototipą, skirtą balso įrašams stenografuoti. Remiantis akustinių modelių testavimo rezultatais galima daryti išvadą, kad pasiektas 94 proc. frazių atpažinimo tikslumas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.