Hi All i'am a new subscriber in this mailing list i'am interesting in the field of HMM for speech synthesis i found a certain PHD thesis For takashi Masuko i hv many questions about many concepts of this thesis y the thesis used the mcp ? why he didn't use any other speech encoding such LPC or MFCC ? y when he tried to generate the cepstral coefficient, why he didn't used the original F0 instead to regenerate it again with the spectrum why he take the Log of the F0 when extract it from the speech databse Thanks Explore the seven wonders of the world Learn more! |