This paper presents a voice transformation algorithm which modifies the speech of a source speaker such that it is perceived as if spoken by a target speaker.
Both the ANN and GMM based models are explored to capture nonlinear mapping functions for modifying the vocal tract characteristics of a source speaker according to a desired target speaker.
Listening tests demonstrate that adapted voices sound more similar to a target speaker than average voices and that differences between supervised and unsupervised cross-lingual speaker adaptation are small.
Dynamic programming approach tries to model the long-term behaviour of LSFs of the target speaker, while it is trying to preserve the relationship between the subsequent frames of the source LSFs, during transformation.
For each test file, there is one trial for the target speaker and nine trials for the non-target speakers.
The neutral speech samples of 300 utterances from each target speaker are collected and used to train the neutral speech model set of that target speaker.
The speaker with the maximum likelihood is determined as the target speaker.
First, statistical synthesis models are generated for a target speaker using a speaker-dependent training algorithm.
(a) CRBMs for a source speaker (below) and a target speaker.
The source speaker was a Japanese male, and the target speaker was a Japanese female.
The speaker with the maximum likelihood was selected as the target speaker.
