G2PU: Grapheme-To-Phoneme Transducer with Speech Units.
Heting GaoMark Hasegawa-JohnsonChang D. YooPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- speech synthesis
- automatic speech recognition
- automatic speech recognition systems
- speaker dependent
- phoneme recognition
- speech signal
- text to speech
- hidden markov models
- speech sounds
- vocal tract
- recognition engine
- speech recognizer
- speaker identification
- noisy environments
- pattern recognition
- speech processing
- speech recognition systems
- vowel phonemes
- prosodic features
- language model
- visual speech
- speaker independent
- speaker adaptation
- spoken language
- maximum likelihood
- speaker verification
- spoken dialogue systems