Adapting machine translation models toward misrecognized speech with text-to-speech pronunciation rules and acoustic confusability
In the spoken language translation pipeline, machine translation systems that are trained
solely on written bitexts are often unable to recover from speech recognition errors due to …
solely on written bitexts are often unable to recover from speech recognition errors due to …
FBK's machine translation and speech translation systems for the IWSLT 2014 evaluation campaign
This paper describes the systems submitted by FBK for the MT and SLT tracks of IWSLT
2014. We participated in the English-French and German-English machine translation tasks …
2014. We participated in the English-French and German-English machine translation tasks …
Speech Adaptation Modeling for Statistical Machine Translation
N Ruiz - 2017 - iris.unitn.it
Spoken language translation (SLT) exists within one of the most challenging intersections of
speech and natural language processing. While machine translation (MT) has demonstrated …
speech and natural language processing. While machine translation (MT) has demonstrated …
[PDF][PDF] Speech Recognition Enhanced by Lightly-supervised and Semi-supervised Acoustic Model Training
S Li - 2016 - repository.kulib.kyoto-u.ac.jp
Automatic transcription of lectures is one of the promising applications of automatic speech
recognition (ASR), since captions to the lectures are needed not only for hearing-impaired …
recognition (ASR), since captions to the lectures are needed not only for hearing-impaired …
[PDF][PDF] Speech Recognition Enhanced by Lightly-supervised and
S Li - science, 2014 - core.ac.uk
Automatic transcription of lectures is one of the promising applications of automatic speech
recognition (ASR), since captions to the lectures are needed not only for hearing-impaired …
recognition (ASR), since captions to the lectures are needed not only for hearing-impaired …