|
I tried to run the Speaker adaptation demo on my own data. Processing directory /home/jisung/HTS-demo-ADAPT/gen/qut001/ver1/SI/0 and /home/jisung/HTS-demo-ADAPT/gen/qut001/ver1/SI+dec_feat3/0 synthesizing a speech waveform “fymn00001.wav” from fymn00001.mgc, fymn00001.b0, fymn00001.dur, fymn00001.lf0, fymn00001.pit in /home/jisung/HTS-demo-ADAPT/gen/qut001/ver1/SI/0. synthesizing an adapted speech waveform “fymn00001.wav” from fymn00001.mgc, fymn00001.b0, fymn00001.dur, fymn00001.lf0, fymn00001.pit in /home/jisung/HTS-demo-ADAPT/gen/qut001/ver1/ SI+dec_feat3/0 I found that all of files have a same values for example fymn00001.mgc, fymn00001.b0, fymn00001.dur, fymn00001.lf0, fymn00001.pit in SI directory and SI+dec_feat3 directory (but speech files “.wav” are different) I wonder why files are same values. SI | SI+dec_feat3 fymn00001.mgc ß-same-à fymn00001.mgc fymn00001.b0 ß-same-à fymn00001.b0 fymn00001.dur ß-same-à fymn00001.dur => Why??? fymn00001.lf0 ß-same-à fymn00001.lf0 . ß-same-à . . ß-same-à . . ß-same-à . ============================= fymn00001.wav ß-differnet-à fymn00001.wav Could you please help me a solution for this? Thanks in advance for any hint
regards, Jisung 25GB 무료 웹하드로 파일 전송을 쉽고 편하게! 무료 웹하드로 안내 보기 |