Adapting machine translation models toward misrecognized speech with text-to-speech pronunciation rules and acoustic confusability

N Ruiz, G Qin, L Will, M Federico - Proceedings of Interspeech 2015, 2015 - cris.fbk.eu
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 …

FBK's machine translation and speech translation systems for the IWSLT 2014 evaluation campaign

N Bertoldi, P Mathur, N Ruiz… - Proceedings of the 11th …, 2014 - aclanthology.org
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 …

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 …

[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 …

[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 …