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...

We present a prototype of the Minnesang exhibit that translates visitors’ utterances into medieval German in their own voice. This lets visitors experience how they would have spoken in medieval times. The project illustrates new variants of voice conversion and their use in human-computer interaction.

In this paper, we propose many-to-many voice conversion (VC) techniques to convert an arbitrary source speaker’s voice into an arbitrary target speaker’s voice. We have proposed one-tomany eigenvoice conversion (EVC) and many-to-one EVC. In the EVC, an eigenvoice Gaussian mixture model (EV-GMM) is trained in advance using multiple parallel data sets of a reference speaker and many pre-stored sp...

Voice conversion, a technique to change one’s voice to sound like that of another, poses a threat to even high performance speaker verification system. Vulnerability of text-independent speaker verification systems under spoofing attack, using statistical voice conversion technique, was evaluated and confirmed in our previous work. In this paper, we further extend the study to text-dependent sp...

Often a face has voice. Appearance sometimes strong relationship with one's In this work, we study how can be converted to voice, which is face-based voice conversion. Since there no clean dataset that contains and speech, conversion faces difficult learning low-quality problems caused by background noise or echo. Too much redundant information for face-to-voice also causes synthesis of general...

Voice conversion techniques aim to modify a subject’s voice characteristics in order to mimic the one’s of another person. Due to the difference in utterance length between source and target speaker, state of the art voice conversion systems often rely on a frame alignment pre-processing step. This step aligns the entire utterances with algorithms such as dynamic time warping (DTW) that introdu...