Acoustic synthesis of training data for speech recognition in living room environments.
Volker StahlAlexander FischerRolf BippusPublished in: ICASSP (2001)
Keyphrases
- speech recognition
- acoustic models
- speech recognition systems
- training data
- speaker independent
- speech recognizer
- speech recognizers
- hidden markov models
- automatic speech recognition
- language model
- speech synthesis
- speech signal
- speech processing
- pattern recognition
- speech recognition technology
- noisy speech
- speech understanding
- noisy environments
- speaker identification
- isolated word
- broadcast news
- training set
- keyword spotting
- training process
- speech retrieval
- machine learning
- neural network
- discriminative training
- cepstral coefficients
- speaker dependent
- classification accuracy