Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures.
Nick RossenbachMohammad ZeineldeenBenedikt HilmesRalf SchlüterHermann NeyPublished in: CoRR (2021)
Keyphrases
- automatic speech recognition
- training data
- speech recognition
- acoustic models
- speech signal
- broadcast news
- hidden markov models
- conversational speech
- word recognition
- speech retrieval
- word error rate
- data sets
- spoken words
- training set
- language model
- acoustic features
- recognition errors
- decision trees
- learning algorithm
- noisy environments
- spontaneous speech
- training process
- pattern recognition
- multiscale
- image processing