Japanese forensic phonetics: non-contemporaneous within-speaker variation in natural and read-out speech.
Yuko KinoshitaPublished in: ICSLP (1998)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- speaker verification
- speech signal
- speaker dependent
- automatic speech recognition systems
- speaker diarization
- vocal tract
- prosodic features
- synthesized speech
- hidden markov models
- emotion recognition
- multi modal
- linear prediction
- broadcast news
- gaussian mixture model
- acoustic features
- audio stream
- phoneme recognition
- multimedia
- speech sounds
- speaker adaptation
- text to speech
- spoken language