In silicon devices, the spectral bandwidth of coherent anti-Stokes Raman scattering (CARS) is limited by the narrowband nature of the Raman process in this medium. In this Letter, we report the observation of broadband wavelength conversion in silicon through CARS enhanced by the self-phase-modulation-induced spectral broadening of the optical pump. The CARS conversion over a bandwidth substant...

Most of the research in Voice Conversion (VC) is devoted to spectral transformation while the conversion of prosodic features is essentially obtained through a simple linear transformation of pitch. These separate transformations lead to an unsatisfactory speech conversion quality, especially when the speaking styles of the source and target speakers are different. In this paper, we propose a m...

This article aims to examine methods of optimizing GMM-based voice conversion systems performance in which GMM method is introduced as the basic method for improvement of voice conversion systems performance. In the current methods, due to using a single conversion function to convert all speech units and subsequent spectral smoothing arising from statistical averaging, we will observe quality ...

Conventional approaches to voice conversion typically use a GMM to represent the joint probability density of source and target features. This model is then used to perform spectral conversion between speakers. This approach is reasonably effective but can be prone to overfitting and oversmoothing of the target spectra. This paper proposes an alternative scheme that uses a collection of Gaussia...

The performance of voice conversion has been considerably improved through statistical modeling of spectral sequences. However, the converted speech still contains traces of artificial sounds. To alleviate this, it is necessary to statistically model a source sequence as well as a spectral sequence. In this paper, we introduce STRAIGHT mixed excitation to a framework of the voice conversion bas...

Two existing speech conversion algorithms were modified and used to enhance alaryngeal speech. The modifications were aimed at reducing spectral distortion (bandwidth increase) in a vector-quantization (VQ) based system and the spectral discontinuity in a linear multivariate regression (LMR) based system. Spectral distortion was compensated for by formant enhancement using chirp z-transform and...

This paper explores the benefits of transforming spectral peaks in voice conversion. First, in examining classic GMMbased transformation with cepstral coefficients, we show that the lack of transformed data variance ("over-smoothing") can be related to the choice of spectral parameterization. Consequently, we propose an alternative parameterization using spectral peaks. The peaks are transforme...