DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System
This addresses the challenge of data scarcity in singing voice conversion for applications like music production, though it is incremental by building on existing synthesis frameworks.
The paper tackles the problem of singing voice conversion with limited singing data by proposing a system that uses only normal speech data from the target speaker to generate high-quality singing, achieving conversion with just 20 seconds of enrollment speech.
Singing voice conversion is converting the timbre in the source singing to the target speaker's voice while keeping singing content the same. However, singing data for target speaker is much more difficult to collect compared with normal speech data.In this paper, we introduce a singing voice conversion algorithm that is capable of generating high quality target speaker's singing using only his/her normal speech data. First, we manage to integrate the training and conversion process of speech and singing into one framework by unifying the features used in standard speech synthesis system and singing synthesis system. In this way, normal speech data can also contribute to singing voice conversion training, making the singing voice conversion system more robust especially when the singing database is small.Moreover, in order to achieve one-shot singing voice conversion, a speaker embedding module is developed using both speech and singing data, which provides target speaker identify information during conversion. Experiments indicate proposed sing conversion system can convert source singing to target speaker's high-quality singing with only 20 seconds of target speaker's enrollment speech data.