Tag
SPARC introduces a benchmark of over 12,500 speakers and 1.5M utterances to study how much speaker identity and demographic attributes can be verified from transcribed speech alone, evaluating attribution models and LLM adversaries. The work finds LLMs can distinguish same-speaker pairs and verify sex/accent labels above chance, while short 50-word excerpts reduce linkage risk.
This paper introduces SI-cpWER, a corpus-level metric for persistent speaker attribution across meetings, and evaluates 5 commercial diarized-STT APIs plus 2 open baselines (and their own ThyVoice system) on NOTSOFAR and CHiME-6, showing that per-meeting ranking doesn't reflect cross-meeting identity consistency. A short version was accepted at IEEE SLT 2026 Demo Track.
This paper challenges the assumption that EER is a reliable proxy for human voice similarity in speech generation, demonstrating that perceptual alignment depends more on training objectives than model performance. It proposes embedding geometry with effective dimensionality as a principled metric for evaluating voice similarity.
This paper presents a simple language normalization method using Nuisance Attribute Projection (NAP) for cross-lingual speaker verification, achieving significant error reduction in the TidyVoice2026 Challenge.
This paper investigates how multimodal speaker verification using audio, prosodic, and linguistic cues across multiple utterances can significantly degrade speaker anonymization, reducing equal error rate by over 15% with only five utterances.
This paper presents a novel speaker verification framework that combines frozen self-supervised features with ECAPA-TDNN and a Mixture of Experts module, using conditional distillation and contrastive loss to improve identity verification across both speech and non-verbal vocalizations while preventing catastrophic forgetting.
This paper proposes a post-training refinement approach using interventional contrastive learning to disentangle speech foundation model representations into separate content and speaker subspaces. The method shows improved out-of-domain speaker verification performance and evidence of successful separation.