Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural Networks.
Micha WetzelMatthias SperberAlexander WaibelPublished in: IWSLT (2016)
Keyphrases
- speech recognition
- neural network
- speech processing
- speaker identification
- pattern recognition
- noisy environments
- speech recognition technology
- hidden markov models
- language model
- speech signal
- automatic speech recognition
- speech synthesis
- audio visual speech recognition
- image segmentation
- speech recognizer
- cepstral coefficients
- signal processing
- speech recognition systems
- visual information
- speech retrieval
- speaker independent
- audio signal
- low level
- speech recognizers
- isolated word
- feature selection