Waveform-based speech synthesis approach with a formant frequency modification.
Hideyuki MizunoMasanobu AbeTomohisa HirokawaPublished in: ICASSP (2) (1993)
Keyphrases
- speech synthesis
- speech recognition
- vocal tract
- speech signal
- fundamental frequency
- text to speech
- prosodic features
- language model
- low frequency
- automatic speech recognition
- hidden markov models
- frequency domain
- pattern recognition
- frequency band
- noisy environments
- spectrum analysis
- frequency response
- speech corpus
- cross correlation
- image formation
- image acquisition
- information retrieval
- data structure
- artificial intelligence
- databases