A 293-speaker longitudinal dataset with weekly samples over up to 17 years is introduced and used to show that speaker verification error grows with age, especially for female and middle-aged speakers.
Data setting As shown in Table 2, the data settings of V oxAging include ”X- Independent” and ”X-Dependent” configurations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin
A 293-speaker longitudinal dataset with weekly samples over up to 17 years is introduced and used to show that speaker verification error grows with age, especially for female and middle-aged speakers.