Detail publikačního výsledku

Voice Conversion Based on Nonlinear Spectrum Transformation

VONDRA, M.

Originální název

Voice Conversion Based on Nonlinear Spectrum Transformation

Anglický název

Voice Conversion Based on Nonlinear Spectrum Transformation

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

In this paper a new voice conversion algorithm is presented, which transforms the utterance of a source speaker into the utterance of a target speaker or into the utterance of a new unknown speaker. The voice conversion algorithm is based on spectral speech analysis, frequency transformation, spectral envelope warping, spectrum interpolation and parametrical high quality IIR or FIR cepstral speech synthesis.

Anglický abstrakt

In this paper a new voice conversion algorithm is presented, which transforms the utterance of a source speaker into the utterance of a target speaker or into the utterance of a new unknown speaker. The voice conversion algorithm is based on spectral speech analysis, frequency transformation, spectral envelope warping, spectrum interpolation and parametrical high quality IIR or FIR cepstral speech synthesis.

Klíčová slova v angličtině

Voice conversion, speech analysis, speech synthesis

Autoři

VONDRA, M.

Vydáno

01.01.2004

Nakladatel

Radio Engineering and Electronics AS CR

Místo

Czech Republic

ISBN

80-86269-11-6

Kniha

SPEECH PROCESSING

Strany od

53

Strany počet

8

BibTex

@inproceedings{BUT14937,
  author="Martin {Vondra} and Robert {Vích}",
  title="Voice Conversion Based on Nonlinear Spectrum Transformation",
  booktitle="SPEECH PROCESSING",
  year="2004",
  number="1",
  pages="8",
  publisher="Radio Engineering and Electronics AS CR",
  address="Czech Republic",
  isbn="80-86269-11-6"
}