07-sources

original corpus recordings vs generated winner B · 7 voices × 4 lines
Round 07 — SOURCE VERIFICATION. Rows SRC_* are the ORIGINAL corpus recordings, untouched — this is what the model learned from. Bottom row = the generated winner B on the same sentences. The theory under test: shigure's recordings have hot sibilants + a hiss floor (measured S-harshness 2.92 vs ~1.5 others, floor ~9x) — listen to SRC_shigure's sib1/sib2 against SRC_ami_pun / SRC_aoba on the same sentences and judge for yourself. Also compare SRC rows vs GEN row: how much of the S noise is inherited from the source (present in SRC_shigure) vs added by the vocoder (present in GEN but not in clean SRC rows).
voice sib1ディスカッションを進める。RECITATION324_208 — densest sibilants (and it contains 進める) sib2社長からの指示です。RECITATION324_049 — sha/shi/ji cluster shortえっ嘘でしょ。EMOTION100_001 casual時間はあるんだから、安全運転してくれよ。EMOTION100_066
SRC_shigureORIGINAL recording from the shigure corpus (untouched file, canonical copy)
SRC_kokoroORIGINAL recording from the kokoro corpus (untouched file, canonical copy)
SRC_ami_punORIGINAL recording from the ami_pun corpus (untouched file, canonical copy)
SRC_ami_normORIGINAL recording from the ami_norm corpus (untouched file, canonical copy)
SRC_aobaORIGINAL recording from the aoba corpus (untouched file, canonical copy)
SRC_ayakaORIGINAL recording from the ayaka corpus (untouched file, canonical copy)
GEN_winnerBgenerated: shig60_koko20_pun20 on boyspace e30_s88925 (compare against sources)