Automatic acoustic segmentation for speech recognition on broadcast recordings.
Gang PengMei-Yuh HwangMari OstendorfPublished in: INTERSPEECH (2007)
Keyphrases
- speech recognition
- speech recognition systems
- speech recognizers
- acoustic features
- speaker independent
- visual speech recognition
- automatic speech recognition
- fully automatic
- speech signal
- hidden markov models
- speech recognizer
- speech synthesis
- pattern recognition
- acoustic models
- noisy speech
- noisy environments
- speech processing
- image segmentation
- language model
- speaker identification
- spontaneous speech
- speech recognition errors
- speech recognition technology
- edge detection
- image processing
- speech retrieval
- computer vision
- neural network
- signal processing
- feature selection
- machine learning