arXiv AI
AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Oct 1
Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings
arXiv:2609.39344v1 Announce Type: cross Abstract: Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ign...
Hugging Face Trending Papers
Sep 30
Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings
Speech transcripts used as long-term memory must preserve both words and stable speaker identities. Existing meeting-transcription metrics either ignore speakers or remap anonymous speakers independen...
arXiv AI
Aug 5
dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model
arXiv:2608. 02673v1 Announce Type: cross Abstract: Speech editing for content creation requires precise control over both what an edit should do and where it should apply.
arXiv Computation and Language
3d ago
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
arXiv:2605.15104v3 Announce Type: replace Abstract: Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling benchmarks remain text-based. We study whether veri...
arXiv AI
Oct 7
Voice "Cloning" is Style Transfer
arXiv:2605.16578v4 Announce Type: replace-cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity pres...