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.
Previous speaker aging datasets As shown in Table 1, existing speaker aging datasets can be classified into two types: discrete and continuous, based on ses- sion intervals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.