| title | SPARC: Spoken Profile Authorship Recognition Corpus |
|---|---|
| authors | Efthymios Tsaprazlis, Bowen Yi, Tiantian Feng, Junghwan Kim, David Jurgens, Shrikanth Narayanan |
| date | 2026-10-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.25265 |
| affiliation | University of Southern California |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker and demographic-attribute verification from transcribed speech. We introduce SPARC (Spoken Profile Authorship Recognition Corpus), a benchmark built from two podcast corpora comprising over 12,500 speakers, 1.5M quality-filtered utterances, and speaker-level inferred or source-provided labels for sex, age, and accent, and evaluate five attribution models and three LLMs on identity- and attribute-verification trials with episode- and metadata-based topic proxies. LLM adversaries distinguish same-speaker pairs from text alone. Attribute-label agreement is harder to verify, but LLMs perform sex- and accent-label verification above chance. Finally, releasing only short probe texts (50 words) degrades the strongest adversaries the most, offering a partial reduction in observed linkage. |
cite
@misc{tsaprazlis2026sparc,
title={SPARC: Spoken Profile Authorship Recognition Corpus},
author={Efthymios Tsaprazlis and Bowen Yi and Tiantian Feng and Junghwan Kim and David Jurgens and Shrikanth Narayanan},
year={2026},
eprint={2610.25265},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.25265}
}