State-of-the art voice conversion methods re-synthesize voice from
spectral representations such as MFCCs and STRAIGHT, thereby
introducing muffled artifacts. We propose a method that circumvents
this concern using concatenative synthesis coupled with exemplarbased
unit selection. Given parallel speech from source and target
speakers as well as a new query from the source, our method
stitches together pieces of the target voice. It optimizes for three
goals: matching the query, using long consecutive segments, and
smooth transitions between the segments. To achieve these goals,
we perform unit selection at the frame level and introduce triphonebased
preselection that greatly reduces computation and enforces
selection of long, contiguous pieces. Our experiments show that
the proposed method has better quality than baseline methods, while
preserving high individuality.