Diphone concatenation using a harmonic plus noise model of speech

@inproceedings{Stylianou1997DiphoneCU,
  title={Diphone concatenation using a harmonic plus noise model of speech},
  author={Yannis Stylianou and Thierry Dutoit and Juergen Schroeter},
  booktitle={EUROSPEECH},
  year={1997}
}
In this paper we present a high-quality text-to-speech system using diphones. The system is based on a Harmonic plus Noise (HNM) representation of the speech signal. HNM is a pitch-synchronous analysis-synthesis system but does not require pitch marks to be determined as necessary in PSOLA-based methods. HNM assumes the speech signal to be composed of a periodic part and a stochastic part. As a result, diierent prosody and spectral envelope modiication methods can be applied to each part… CONTINUE READING