Automatic acoustic segmentation in N-best list rescoring for lecture speech recognition.
Peng ShenXugang LuHisashi KawaiPublished in: ISCSLP (2016)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- visual speech recognition
- speech recognizers
- fully automatic
- acoustic models
- language model
- hidden markov models
- pattern recognition
- speech recognizer
- noisy speech
- speech processing
- image segmentation
- speech synthesis
- speech recognition technology
- speaker identification
- handwriting recognition
- automatic speech recognition
- speech signal
- word error rate
- speaker dependent
- noisy environments
- computer vision
- neural network
- speech retrieval
- image processing