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