ESPnet: End-to-End Speech Processing Toolkit.
Shinji WatanabeTakaaki HoriShigeki KaritaTomoki HayashiJiro NishitobaYuya UnnoNelson Enrique Yalta SoplinJahn HeymannMatthew WiesnerNanxin ChenAdithya RenduchintalaTsubasa OchiaiPublished in: INTERSPEECH (2018)
Keyphrases
- end to end
- speech processing
- signal processing
- speech recognition
- multimedia systems
- natural language processing
- speaker identification
- artificial intelligence
- admission control
- english text
- congestion control
- machine learning
- variable length
- maximum likelihood
- application layer
- information extraction
- hidden markov models
- image processing
- natural language
- database systems
- information retrieval