Speech recognition with large-scale speaker-class-based acoustic modeling.
Kazuki KonnoMasaharu KatoTetsuo KosakaPublished in: APSIPA (2013)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- automatic speech recognition
- acoustic models
- hidden markov models
- speech processing
- speaker dependent
- speech signal
- speech synthesis
- speaker identification
- pattern recognition
- speech recognizer
- speaker diarization
- noisy speech
- language model
- speech understanding
- keyword spotting
- noisy environments
- speaker adaptation
- acoustic features
- speech recognition technology
- speech retrieval
- probabilistic model
- speaker verification
- cepstral coefficients
- signal processing
- speech recognition errors
- isolated word