Acoustic Feature Analysis and Discriminative Modeling of Filled Pauses for Spontaneous Speech Recognition.
Chung-Hsien WuGwo-Lang YanPublished in: J. VLSI Signal Process. (2004)
Keyphrases
- speech recognition
- feature analysis
- speech signal
- speech recognition systems
- speech synthesis
- speaker independent
- speech recognizers
- hidden markov models
- speech processing
- language model
- automatic speech recognition
- feature extraction
- pattern recognition
- acoustic models
- speech recognizer
- noisy speech
- speaker identification
- noisy environments
- speech recognition technology
- acoustic features
- semi supervised
- machine learning
- audio visual speech recognition
- speaker dependent
- speech retrieval
- isolated word
- data mining
- probabilistic model
- conversational speech
- discriminative training
- speaker recognition
- unsupervised learning
- signal processing
- neural network