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