Streaming Joint Speech Recognition and Disfluency Detection.
Hayato FutamiEmiru TsunooKentaro ShibataYosuke KashiwagiTakao OkudaSiddhant AroraShinji WatanabePublished in: ICASSP (2023)
Keyphrases
- speech recognition
- hidden markov models
- noisy environments
- speech processing
- speech signal
- automatic speech recognition
- language model
- speech recognizer
- speech synthesis
- pattern recognition
- speech recognition technology
- speech recognition systems
- voice activity detection
- speech understanding
- speaker independent
- speaker identification
- speech retrieval
- speaker recognition
- keyword spotting
- speech recognition errors
- non stationary
- speaker diarization
- visual features
- cepstral coefficients
- bayesian networks
- isolated word