Dynamic Frame Skipping for Fast Speech Recognition in Recurrent Neural Network Based Acoustic Models.
Inchul SongJunyoung ChungTaesup KimYoshua BengioPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- acoustic models
- speaker independent
- hidden markov models
- speech recognizer
- automatic speech recognition
- pattern recognition
- language model
- speech signal
- speaker identification
- neural network
- speech recognition systems
- noisy environments
- information extraction
- generative model
- mixture model
- machine learning