Pre-training on high-resource speech recognition improves low-resource speech-to-text translation.
Sameer BansalHerman KamperKaren LivescuAdam LopezSharon GoldwaterPublished in: CoRR (2018)
Keyphrases
- speech recognition
- hidden markov models
- wall street journal corpus
- speech synthesis
- pattern recognition
- speech recognition technology
- language model
- isolated word
- automatic speech recognition
- speaker identification
- speech signal
- speech processing
- discriminative training
- speech retrieval
- speech recognition systems
- speech recognizer
- noisy environments
- training set
- machine learning
- training process
- machine translation
- speaker independent
- information extraction
- speech recognizers
- image processing
- computer vision