i
Diese Präsentation ist für die Ansicht im Querformat gestaltet.
Output of Primer's ASR system combining DeepSpeech acoustic model with language model specific to German-verb recognition exercise.
in majority of reading exercises which are included in the Primer we already know the text in advance
we already know what utterances could be considered as correct lectures and which not
to every specific exercise - like vowel or syllable recognition – Primer associates a specific language model (scorer) which constraints the connectionist temporal classification (CTC) beam search to restricted amount of exercise-relevant answers
significantly constraining the search space of plausible solutions
INNOVATION 1 : implementation of exercise-specific scorers transforms a generic ASR problem (difficult) into multi-class classification problem (easier)