“...碩士 === 國立臺灣科技大學 === 資訊工程系 === 98 === In this thesis, a GMM based voice conversion method...”
Get full text

“...碩士 === 國立臺灣科技大學 === 資訊工程系 === 103 === Is this thesis, we propose singing voice signal segmentation...”
Get full text

“...碩士 === 國立臺灣科技大學 === 資訊工程系 === 97 === In this thesis, synthesis of English singing voices is studied...”
Get full text

“... two GMM based on pseudo-divergence. Then, two different clustering methods, approximated k-means...”
Get full text

“... the method for detecting the pitch of a signal frame, use dynamic threshold to determine the maximum-voiced...”
Get full text

“.... The recognition method studied is based on Gaussian mixture model (GMM). Different numbers of mixtures, e.g. 8, 16...”
Get full text

“... to improve the converted voice quality. Also, we notice that parallel training sentences are hard to prepare...”
Get full text

“... singing voices through unit selection, this thesis aims to keep the signal quality and timbre...”
Get full text

“...碩士 === 國立臺灣科技大學 === 資訊工程系 === 104 === In this thesis, a combination method for voice conversion...”
Get full text

“...), are processed separately. The name of our method is just selected to reflect the voiced-part...”
Get full text