Papers for

podcast platform teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Spoken words alone reveal speaker identity and some attributes

SPARC: Spoken Profile Authorship Recognition Corpus

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.

Sun 18 OctComputation and Language
The gist
People often think that if they only share what they say, and not their voice, their identity stays private. This paper shows that by looking only at the written words from speech, computers can still often tell if two pieces come from the same person. The researchers created a large collection of podcast speech transcripts and tested different models, including advanced language models, to see if these models could recognize who spoke or their sex and accent. They found that while it's easier to identify the speaker than to confirm demographic details, limiting text samples to short pieces can reduce but not eliminate this risk.
Open → 2610.25265v1

Cue grounded method improves spoken topic segmentation with zero training

Zero-Shot Cue-Grounded Topic Segmentation of Spoken Documents

Abstract: Topic segmentation structures spoken documents into coherent sections, facilitating navigation and downstream understanding. The appropriate granularity can vary substantially, ranging from broad thematic shifts to fine-grained subtopics. Existing LLM-based segmenters, however, often struggle to adapt to this variation, causing them to either merge distinct subtopics or over-segment coherent themes. To address this, we introduce Cue-Grounded Segmentation (CGS), a training-free framework that operates without any task-specific supervision. CGS first identifies phrases that explicitly signal the start of a new topic and uses their sentence positions as segment boundaries. When such cues are insufficient, it falls back to semantic segmentation, guided by the document structure inferred during cue extraction. Across six benchmarks and six LLM backbones, CGS consistently outperforms existing baselines, remains robust to noisy ASR transcripts, and achieves these gains with low API cost on proprietary models.

Mon 28 SeptComputation and LanguageArtificial Intelligence
The gist
Breaking long spoken documents into topics helps people find and understand information better, but it's hard to do this well when topics vary in size. The authors designed a new way that doesn't require teaching the computer beforehand. Their method looks for special words or phrases that usually signal a new topic, and if those aren't clear, it uses the overall meaning to guess where topics change. This method works better than others, even with imperfect speech-to-text transcripts, and is cheaper to run with big language models.
Open → 2609.34425v1