A new multi-speaker formant synthesizer that applies voice conversion techniques.
Juana M. Gutiérrez-ArriolaJuan Manuel MonteroJosé A. VallejoRicardo de CórdobaRubén San SegundoJosé Manuel PardoPublished in: INTERSPEECH (2001)
Keyphrases
- text to speech
- speech recognition
- vocal tract
- speech synthesis
- prosodic features
- speaker verification
- synthesized speech
- automatic speech recognition
- information systems
- speech signal
- pattern recognition
- speaker identification
- real time
- word processing
- hidden markov models
- voice recognition
- speaker adaptation
- neural network