Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis

Submitted to ICASSP 2025

Source code available at https://github.com/ljuvela/collaborative-watermarking-with-codecs

Following LibriTTS-R dataset, audio samples on this page are distributed following Creative Commons License: Attribution 4.0 International (CC BY 4.0).

Please select the utterance ID from the menu. The page will load the corresponding audio samples.

121_121726_000029_000003 237_126133_000055_000003 237_134493_000007_000000 237_134493_000022_000000 237_134500_000004_000001 237_134500_000031_000000 237_134500_000036_000005 260_123286_000042_000000 260_123288_000004_000001 260_123288_000007_000001 260_123288_000015_000000 260_123440_000010_000002 260_123440_000021_000001 1089_134691_000025_000000 1188_133604_000012_000003 1284_1181_000028_000001 1320_122612_000005_000001 1320_122612_000056_000003 1580_141083_000083_000001 1580_141084_000057_000000 1995_1836_000007_000001 1995_1836_000030_000000 3570_5694_000007_000005 3570_5694_000014_000006 3570_5696_000004_000004 3575_170457_000029_000000 4446_2271_000022_000010 4446_2273_000003_000000 4446_2273_000011_000003 4446_2273_000035_000002 4446_2273_000035_000004 5105_28241_000005_000000 5105_28241_000021_000001 5639_40744_000018_000002 5683_32865_000012_000000 5683_32879_000047_000000 6829_68769_000017_000001 6829_68769_000062_000000 6829_68769_000096_000001 6930_75918_000038_000000 7021_79730_000062_000000 7021_85628_000036_000001 7127_75946_000060_000005 7127_75947_000082_000005 7176_88083_000024_000003 8230_279154_000024_000007 8455_210777_000075_000000 8463_294825_000017_000001 8463_294828_000021_000000 8555_284447_000047_000000