We have previously developed a one-to-many eigenvoice conversion (EVC) system enabling the conversion from a specific source speaker’s voice into an arbitrary target speaker’s voice. In this system, eigenvoice Gaussian mixture model (EV-GMM) is trained in advance with multiple parallel data sets composed of utterance pairs of the source and many pre-stored target speakers. The EV-GMM is effecti...

Most Voice Conversion (VC) systems exploit source-filter decomposition based on linear prediction (LP) to transform spectral envelopes, incurring as a result various issues related to the oversimplification of the LP voice source model. Whilst residual prediction methods can mitigate this problem, they cannot be used to modify voice source quality. In this paper, a system which employs linear t...

Introduction: Laryngeal burns cause long-term voice disorders due to mucosal changes of the vocal folds. Inhalation injuries affect voice production and result in changes in the mucosal thickness and voice quality.   Case Report: A 47-year-old woman was transferred to our department with laryngeal burns sustained during a house fire. On laryngoscopic examination, mucosal waves of both vocal fol...

This paper presents a duration-embedded Bi-HMM framework for expressive voice conversion. First, Ward’s minimum variance clustering method is used to cluster all the conversion units (sub-syllables) in order to reduce the number of conversion models as well as the size of the required training database. The duration-embedded Bi-HMM trained with the EM algorithm is built for each sub-syllable cl...

Voice conversion involves transformation of speaker characteristics in a speech uttered by a speaker called source speaker so as to generate a speech having voice characteristics of a desired speaker called target speaker. Voice conversion technology is used in many applications namely dubbing, to enhance the quality of the speech, text-to-speech synthesizers, online games, multimedia, music, c...

Recently, a number of voice conversion methods have been developed. These methods attempt to improve conversion performance by using diverse mapping techniques in various acoustic domains, e.g. high-resolution spectra and low-resolution Mel-cepstral coefficients. Each individual method has its own pros and cons. In this paper, we introduce a system fusion framework, which leverages and synergiz...

We present here our work in automatic parameterization of natural speech by means of a pitch synchronous source-filter decomposition algorithm. The derivative glottal source is modelled using the Liljencrants-Fant (LF) model. The model parameters are obtained simultaneously with the coefficients of an all-pole filter representing the vocal tract response by means of a quadratic programming algo...

This paper presents adaptive voice-quality control methods based on one-to-many eigenvoice conversion. To intuitively control the converted voice quality by manipulating a small number of control parameters, a multiple regression Gaussian mixture model (MR-GMM) has been proposed. The MR-GMM also allows us to estimate the optimum control parameters if target speech samples are available. However...

This paper proposes techniques for flexibly controlling voice quality of converted speech from a particular source speaker based on one-to-many eigenvoice conversion (EVC). EVC realizes a voice quality control based on the manipulation of a small number of parameters, i.e., weights for eigenvectors, of an eigenvoice Gaussian mixture model (EV-GMM), which is trained with multiple parallel data s...

Speaker identity is one of the important characteristics human speech. In voice conversion, we change speaker from to another, while keeping linguistic content unchanged. Voice conversion involves multiple speech processing techniques, such as analysis, spectral prosody characterization, and vocoding. With recent advances in theory practice, are now able produce human-like quality with high sim...