An Exploration of Directly Using Word as ACOUSTIC Modeling Unit for Speech Recognition.
Chunlei ZhangChengzhu YuChao WengJia CuiDong YuPublished in: SLT (2018)
Keyphrases
- speech recognition
- speech recognition systems
- speech recognizers
- speech recognizer
- wall street journal corpus
- hidden markov models
- speaker independent
- speech synthesis
- automatic speech recognition
- language model
- speech processing
- pattern recognition
- acoustic models
- speech recognition technology
- keyword spotting
- speech signal
- noisy environments
- speaker dependent
- speech recognition errors
- speech retrieval
- speaker identification
- speaker diarization
- n gram
- feature selection
- acoustic features
- speaker recognition