End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining.
Saksham BassiGiulio DuregonSiddhartha JalagamDavid RothPublished in: CoRR (2023)
Keyphrases
- end to end
- speech recognition
- language model
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- language modeling
- automatic speech recognition
- speech recognizer
- n gram
- document retrieval
- probabilistic model
- spontaneous speech
- information retrieval
- retrieval model
- speech signal
- speech synthesis
- acoustic features
- test collection
- speaker identification
- noisy environments
- query expansion
- mixture model
- handwriting recognition
- translation model
- word error rate
- sound source
- statistical machine translation
- relevance model
- machine learning
- query terms
- mobile devices
- pattern recognition