Investigation on N-gram Approximated RNNLMs for Recognition of Morphologically Rich Speech.
Balázs TarjánGyörgy SzaszákTibor FegyóPéter MihajlikPublished in: CoRR (2019)
Keyphrases
- n gram
- recognition engine
- language model
- finite state transducers
- speech recognition
- text classification
- bag of words
- language modeling
- language independent
- language modelling
- variable length
- part of speech
- speech corpus
- word segmentation
- out of vocabulary
- viterbi algorithm
- action recognition
- word recognition
- speech signal
- web documents
- inside outside algorithm
- knowledge discovery
- character n grams
- document analysis
- relevance feedback