Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models.
Naoyuki KandaShota HoriguchiYusuke FujitaYawen XueKenji NagamatsuShinji WatanabePublished in: ASRU (2019)
Keyphrases
- speech recognition
- speaker diarization
- acoustic models
- speech recognizer
- speaker independent
- automatic speech recognition
- hidden markov models
- language model
- pattern recognition
- broadcast news
- speaker identification
- acoustic features
- speech signal
- noisy environments
- dialogue system
- word error rate
- mel frequency cepstral coefficients
- speech recognition systems