4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Voice Conversion Based on Topological Feature Maps and Time-variant Filtering

Ansgar Rinscheid

Lehrstuhl für allgemeine Elektrotechnik und Akustik, Ruhr-Universität Bochum, Germany

This paper presents a new voice conversion algorithm. This algorithm allows voices to be adapted using a small amount of adaptation data. Only a few short adaptation units (phonemes or short words) are needed. The voice conversion is performed using a time-variant digital filter, topological feature maps and a map of filter coefficients. The filter coefficients of the time-variant filter are selected by the feature map dependent on the short-time spectrum. The spectral envelope of the input signal is modified by a time-variant filter using the selected coefficients.

Full Paper
Sound Examples:   #01   #02   #03   #04   #05   #06   #07   #08   #09   #10   #11  

Bibliographic reference.  Rinscheid, Ansgar (1996): "Voice conversion based on topological feature maps and time-variant filtering", In ICSLP-1996, 1445-1448.