other · OpenGrey (Institut de l'Information Scientifique et Technique) · 2007

Voice Morphing

Orphanidou, Christina

Cited by 0Abstract and details only

Abstract

Voice Morphing is the process of modifying a source speaker's speech so that it is perceived as if uttered by a target speaker. The numerous applications of this technology have made it a very popular research topic with most approaches focusing on transforming the spectral envelope of the source speaker to match that of the target speaker. This is usually achieved by estimating a transformation function from parallel training data from the two speakers. However, the current applications suffer from loss of spectral detail during synthesis of the morphed speech, often attributed to the low dimensional representations of the acoustic models used for extracting the acoustic features. We propose a new Multiresolution Voice Morphing Algorithm (MVMA) which uses the Discrete Wavelet Transform (DWT) for modeling the shortterm and long-term acoustic properties of speech and estimates a transformation function at each sub-band by means of a Radial Basis Function (RBF) neural network. The proposed system is evaluated objectively and subjectively using parallel and non-parallel training data. The tests show that the proposed approach effectively transforms speaker identity even though perceivable artifacts still exist in the transformed speech.

Cite this paper

APA 7

Orphanidou, C. (2007). Voice Morphing. OpenGrey (Institut de l'Information Scientifique et Technique).

MLA 9

Orphanidou, Christina. “Voice Morphing.” OpenGrey (Institut de l'Information Scientifique et Technique), 2007.

Chicago

Orphanidou, Christina. 2007. “Voice Morphing.” OpenGrey (Institut de l'Information Scientifique et Technique).

Harvard

Orphanidou, C. (2007) ‘Voice Morphing’, OpenGrey (Institut de l'Information Scientifique et Technique).

BibTeX

@misc{orphanidou2007voice,
  title = {{Voice Morphing}},
  author = {Orphanidou, Christina},
  journal = {OpenGrey (Institut de l'Information Scientifique et Technique)},
  year = {2007}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.