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
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...
By Shantanu Vispute, Aditya Mishra, Siddhartha Saxena
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: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.
By Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Colin Zhang, Kai Yu
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...
By Md Tahmid Rahman Laskar, Xue-Yong Fu, Seyyed Saeed Sarfjoo, Quinten McNamara, Jonas Robertson, Shashi Bhushan TN
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...
By Kaitlyn Zhou, Federico Bianchi, Martijn Bartelds, Anna Pot, Yongchan Kwon, James Zou
arXiv:2608. 06424v1 Announce Type: cross Abstract: Speech recordings often contain missing, corrupted, or incorrect regions that must be reconstructed or modified without re-synthesizing the entire utterance.
By Iftach Shoham, Tali Dror, Oren Gal, Haim Permuter, Gilad Katz, Eliya Nachmani
arXiv:2609.20995v1 Announce Type: cross
Abstract: Natural spoken interaction requires more than streaming ASR, language generation, and speech synthesis: a system must react to overlap without cancel...
By Bertil Braun
arXiv:2609.38491v1 Announce Type: new
Abstract: Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Y...
By Joseph T Colonel, Daniel Katzman, Kelsey Kirker, Adam N Davidson, Shalaila S Haas, Cheryl Corcoran, Ren\'{e} S Kahn, Guillermo Checci, Baihan Lin
arXiv:2607. 22304v1 Announce Type: new Abstract: Synthetic data augmentation in speech is common practice for linguistic tasks like ASR, but has seen far less work for paralinguistic ones, especially clinical tasks where labelled data is expensive and some patient groups are underrepresented.
By Roseline Polle, Owen Parsons, George Fairs, Luis Miguel San Martin Fernandez, Cole Looney, Xiaoliang Wu, Alexandra Livia Georgescu, Stefano Goria
The paper evaluates whether audio‑language models can use multimodal clinical context to improve dysarthric speech recognition. Using a benchmark built on the Speech Accessibility Project dataset, the authors test diagnosis labels, clinician ratings, and detailed clinical descriptions as prompts for nine models. They find that these prompts yield negligible or negative effects on word error rate, though fine‑tuning with LoRA and mixed prompt formats reduces WER by 52% and benefits certain subgroups such as Down syndrome and mild‑severity speakers.
By Pehu\'en Moure, Niclas Pokel, Bilal Bounajma, Yingqiang Gao, Roman Boehringer, Longbiao Cheng, Shih-Chii Liu
The paper introduces a validation‑gated audit framework for voice AI customer‑care systems, treating them as stateful, multi‑turn, tool‑mediated interactions where bias and safety can manifest as added burdens before a final decision. The framework distinguishes between native speech‑to‑speech, cascaded ASR‑to‑LM‑to‑TTS, and hybrid architectures, and applies matched service facts across controlled caller presentation conditions to validate fact invariance, presentation cues, artifacts, and acoustic measurements. It outlines seven validation gates, a six‑family metric set, and demonstrates the approach with a synthetic refund‑dispute audit example, while noting that production results are withheld until the protocol is satisfied.
By Vignesh Ethiraj, Ashwath David