Adding filled pauses and disfluent events into language models for speech recognition.
Ján StasDaniel HládekJozef JuhárPublished in: CogInfoCom (2016)
Keyphrases
- speech recognition
- language model
- speech signal
- speech synthesis
- language modeling
- probabilistic model
- n gram
- document retrieval
- automatic speech recognition
- query expansion
- retrieval model
- information retrieval
- noisy environments
- speech recognizer
- speaker identification
- smoothing methods
- handwriting recognition
- word error rate
- computer vision
- translation model
- speech recognition systems
- mixture model
- multi modal
- maximum likelihood
- pattern recognition
- relevance model
- neural network