Do End-to-End Speech Recognition Models Care About Context?
Lasse BorgholtJakob D. HavtornZeljko AgicAnders SøgaardLars MaaløeChristian IgelPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- speech processing
- speech synthesis
- acoustic models
- speech recognizer
- language model
- speech signal
- noisy environments
- congestion control
- speech recognition technology
- audio visual speech recognition
- feature extraction
- speech recognizers
- speech retrieval
- speaker dependent
- speaker adaptation
- speaker identification
- pattern recognition