Language model integration based on memory control for sequence to sequence speech recognition.
Jaejin ChoShinji WatanabeTakaaki HoriMurali Karthick BaskarHirofumi InagumaJesús VillalbaNajim DehakPublished in: CoRR (2018)
Keyphrases
- speech recognition
- language model
- language modeling
- automatic speech recognition
- information retrieval
- word error rate
- document retrieval
- n gram
- speech synthesis
- pattern recognition
- hidden markov models
- speech recognizer
- probabilistic model
- query expansion
- speech signal
- ad hoc information retrieval
- speaker identification
- retrieval model
- query terms
- noisy environments
- generative model
- error rate
- machine learning
- speaker independent
- mixture model