Simultaneous Speech Recognition and Acoustic Event Detection Using an LSTM-CTC Acoustic Model and a WFST Decoder.
Hiroshi FujimuraManabu NagaoTakashi MasukoPublished in: ICASSP (2018)
Keyphrases
- event detection
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- hidden markov models
- speech recognizer
- noisy speech
- speech signal
- automatic speech recognition
- video event detection
- video analysis
- activity recognition
- pattern recognition
- event recognition
- acoustic features
- speaker identification
- noisy environments
- speech synthesis
- language model
- n gram
- image retrieval