Search Results for author: Timofey Arkhangelskiy

Found 10 papers, 0 papers with code

Improving the Language Model for Low-Resource ASR with Online Text Corpora

no code implementations LREC 2020 Nils Hjortnaes, Timofey Arkhangelskiy, Niko Partanen, Michael Rie{\ss}ler, Francis Tyers

Previous experiments showed that transfer learning using DeepSpeech can improve the accuracy of a speech recognizer for Komi, though the error rate remained very high.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Eastern Armenian National Corpus: State of the Art and Perspectives

no code implementations DigitAm (LREC) 2022 Victoria Khurshudyan, Timofey Arkhangelskiy, Misha Daniel, Vladimir Plungian, Dmitri Levonian, Alex Polyakov, Sergei Rubakov

Eastern Armenian National Corpus (EANC) is a comprehensive corpus of Modern Eastern Armenian with about 110 million tokens, covering written and oral discourses from the mid-19th century to the present.

Cannot find the paper you are looking for? You can Submit a new open access paper.