A technique for using multipulse linear predictive speech synthesis in text-to-speech type systems
暂无分享,去创建一个
A scheme for alteration of pitch and timing in multipulse linear predictive synthesized speech is presented. The method is a hybrid of waveform coding and linear prediction. It attempts to combine the high-quality sound units available in waveform techniques with the ability to alter prosody available from linear prediction.
[1] B. Atal,et al. Changing pitch and duration in LPC synthesized speech using multipulse excitation , 1983 .
[2] Andrej Ljolje,et al. Synthesis of natural sounding pitch contours in isolated utterances using hidden Markov models , 1986, IEEE Trans. Acoust. Speech Signal Process..
[3] Bishnu S. Atal,et al. A new model of LPC excitation for producing natural-sounding speech at low bit rates , 1982, ICASSP.
[4] John E. Markel,et al. Linear Prediction of Speech , 1976, Communication and Cybernetics.