arXiv AI

Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification

The paper "Beyond EER: Multi-Dimensional Evaluation of Information Leakage in Speaker De-Identification" argues that evaluating speaker de-identification systems solely by Equal Error Rate (EER) is insufficient. It proposes a holistic framework using five complementary metrics—EER, soft biometric leakage score, cumulative match characteristic re-identification analysis, canonical correlation analysis with Procrustes embedding alignment, and intelligibility via word error rate and semantic similarity—to capture independent dimensions of information leakage. Experiments on five IARPA ARTS SDID systems show that these metrics reveal leakage that a single metric would miss.

arXiv Computation and Language

Aug 24

The Voiceprint Fallacy: Why Voices Are Not Unique Biometric Imprints

The article critiques the notion that a person's voice is a stable, unique biometric trace—termed a voiceprint—by reviewing historical, forensic, and technological evidence. It argues that voices are highly dynamic and context-dependent, and that the voiceprint metaphor misrepresents probabilistic speaker information as a fixed identity marker. The authors emphasize that speaker recognition should account for within-speaker variability, domain mismatch, and synthetic manipulation rather than rely on an assumed stable voiceprint.

By Tianle Yang, Cuiling Zhang, Chengzhe Sun, Siwei Lyu, Phil Rose

robotics

arXiv Machine Learning

Jul 27

Probing Speaker Identity Sensitivity in Audio Deepfake Detectors

arXiv:2607. 21820v1 Announce Type: cross Abstract: Audio deepfake detectors are trained to distinguish genuine speech from synthetic speech and often perform well on standard benchmarks.

By Daniyal Kabir Dar, Arun Ross

robotics benchmarks

arXiv AI

Sep 4

Anonymization, Not Elimination: Utility-Preserved Speech Anonymization

The paper introduces a two‑stage speech anonymization framework that preserves both linguistic content and acoustic identity. It replaces personally identifiable information using a generative editing model and applies a flow‑matching anonymization technique (F3‑VA) to create diverse, distinct anonymized speakers. The authors evaluate privacy with speaker verification metrics and utility by training ASR, TTS, and SER models from scratch, showing stronger privacy protection with minimal utility loss compared to existing baselines.

By Yunchong Xiao, Yuxiang Zhao, Ziyang Ma, Shuai Wang, Kai Yu, Jiachun Liao, Xie Chen

multimodal safety

arXiv Computation and Language

Aug 25

Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction

arXiv:2608.22196v1 Announce Type: cross Abstract: While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during sepa...

By Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness, Suresh Singh

efficiency multimodal benchmarks safety

arXiv AI

Jul 7

NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization

arXiv:2607. 03985v1 Announce Type: cross Abstract: Advanced neural technologies in speech synthesis and voice conversion (VC) have introduced severe risks to personal privacy, necessitating robust Speaker Anonymization Systems (SAS).

By Meiying Melissa Chen, Anastasia Kuznetsova, Zhenyu Wang, Zhiyao Duan

rag benchmarks safety

arXiv AI

4d ago

Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech

arXiv:2603.07551v3 Announce Type: replace-cross Abstract: Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Genera...

By Thanathai Lertpetchpun, Thanapat Trachu, Sai Praneeth Karimireddy, Shrikanth Narayanan

multimodal safety

Hugging Face Trending Papers

Jul 27

ScoreShield: Differentially Private Release of Similarity Scores

A growing number of applications, such as biometrics and retrieval-augmented generation (RAG), rely on cosine similarity scores computed between vector embeddings of text, images, or audio. These systems return similarity scores through their APIs for ranking and verification.

rag safety

arXiv AI

Jul 7

DETECT-3B-Omni is Agnostic of Content and Demographics

arXiv:2607. 03418v1 Announce Type: cross Abstract: A trustworthy and GDPR-compliant deepfake audio detector must base its decisions on acoustic artifacts, not on what is being said or who is speaking.

By Nicolas M. M\"uller, Aditya Tirumala Bukkapatnam, Dominik Schnieders, Zohaib Ahmed

arXiv AI

Aug 10

LSEAD: A Privacy-Preserving LLM-Based Speech Analysis Framework for Early Alzheimer's Disease Screening

arXiv:2608. 07378v1 Announce Type: cross Abstract: Early diagnosis of Alzheimer's disease (AD) is critical for enabling timely interventions that may slow disease progression and improve patient outcomes.

By Xin Wang, Yingchao Huang, Yuhan Su, Shanshan Yao, Wei Peng

llms rag benchmarks safety

arXiv Machine Learning

Sep 3

Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models

The paper introduces a black-box membership inference attack framework tailored for fine-tuned text-to-speech models, addressing challenges in query generation and representation engineering. It evaluates five query types, finding recitation queries most effective, and uses multi-level speech embeddings with temporal alignment for fine-grained comparison. Experiments on CosyVoice2, F5-TTS, and XTTS-v2 trained on VCTK and British Dialect datasets show high privacy leakage, with speaker-level AUC above 0.80 and record-level AUC between 0.80 and 0.90.

By Kunlin Cai, Kaiyuan Zhang, Zihang Xiang, Jinghuai Zhang, Abeer Alwan, Fnu Suya, Yuan Tian

rag fine-tuning multimodal benchmarks safety

arXiv AI

Jun 29

DG^VoiC: Speaker Clustering for Fraud Investigation under Real Call-Centre Conditions

arXiv:2606. 28048v1 Announce Type: cross Abstract: Insurance fraud remains costly and operationally difficult, particularly in call-centre workflows where many customer interactions begin at FNOL.

By Muhammad Shakeel Akram, Amal Htait, Abdul Hamid Sadka, Emma Meisingseth, Karishma Jaitly

rag

arXiv Machine Learning

Jun 9

Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

arXiv:2606. 08678v1 Announce Type: cross Abstract: Sophisticated generative speech technology can undermined the reliability of voice biometrics.

By Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier, Nicholas Evans

robotics safety

Related stories