NAIST’s NMT system submitted to the IWSLT 2020 conversational speech translation task . We focus on the translation disfluent speech transcripts that include ASR errors and non-grammatical utterances . We tried a domain adaptation method by transferring the styles of out-of-domain data (United Nations Parallel Corpus) to be like in- domain data (Fisher transcripts)

Links: PDF - Abstract

Code :


Keywords : translation - domain - speech - naist - data -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)