Tootfinder

Any-to-any Speaker Attribute Perturbation for Asynchronous Voice Anonymization
Liping Chen, Chenyang Guo, Rui Wang, Kong Aik Lee, Zhenhua Ling
https://arxiv.org/abs/2508.15565 h…

Any-to-any Speaker Attribute Perturbation for Asynchronous Voice Anonymization
Speaker attribute perturbation offers a feasible approach to asynchronous voice anonymization by employing adversarially perturbed speech as anonymized output. In order to enhance the identity unlinkability among anonymized utterances from the same original speaker, the targeted attack training strategy is usually applied to anonymize the utterances to a common designated speaker. However, this strategy may violate the privacy of the designated speaker who is an actual speaker. To mitigate this…

The FBI is searching the Maryland home and Washington office of
John Bolton, who served in President Donald Trump’s first administration as national security adviser
but later became critical of the president,
as part of an investigation into the handling of classified information.
Bolton was not detained and has not been charged with any crimes

FBI searches home of ex-Trump national security adviser Bolton
The FBI is searching the Maryland home and Washington office of ex-Trump national security adviser John Bolton as part of an investigation into the handling of classified information. That's according to a person familiar with the matter Friday. The person was not authorized to discuss the investigation by name and spoke on the condition of anonymity. The person says Bolton was not detained and has not been charged with any crimes. FBI Director Kash Patel says cryptically online, “NO ONE is a…

Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems
Natalia Tomashenko, Emmanuel Vincent, Marc Tommasi
https://arxiv.org/abs/2507.15214

Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems
The temporal dynamics of speech, encompassing variations in rhythm, intonation, and speaking rate, contain important and unique information about speaker identity. This paper proposes a new method for representing speaker characteristics by extracting context-dependent duration embeddings from speech temporal dynamics. We develop novel attack models using these representations and analyze the potential vulnerabilities in speaker verification and voice anonymization systems.The experimental resu…

Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling
Xuanru Zhou, Jiachen Lian, Cheol Jun Cho, Tejas Prabhune, Shuhe Li, William Li, Rodrigo Ortiz, Zoe Ezzes, Jet Vonk, Brittany Morin, Rian Bogley, Lisa Wauters, Zachary Miller, Maria Gorno-Tempini, Gopala Anumanchipalli
https://arxiv.org/abs/2507.14346…

Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling
Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current models failing to capture these discrepancies effectively. We propose a verbatim phoneme recognition framework using multi-task training with novel phoneme similarity modeling that transcribes what speakers actually say rather than what they're supposed to s…

The Impact of Automatic Speech Transcription on Speaker Attribution
Cristina Aggazzotti, Matthew Wiesner, Elizabeth Allyn Smith, Nicholas Andrews
https://arxiv.org/abs/2507.08660 …

The Impact of Automatic Speech Transcription on Speaker Attribution
Speaker attribution from speech transcripts is the task of identifying a speaker from the transcript of their speech based on patterns in their language use. This task is especially useful when the audio is unavailable (e.g. deleted) or unreliable (e.g. anonymized speech). Prior work in this area has primarily focused on the feasibility of attributing speakers using transcripts produced by human annotators. However, in real-world settings, one often only has more errorful transcripts produced b…

Millions of public euros subsidize bullfighting through regional televisions https://www.animanaturalis.org/n/46882?utm_source=Mastodon
Madrid raises its voice against bullfighting and for a cruelty-free culture

Millions of public euros subsidize bullfighting through regional televisions
We reveal the hidden cost of public funding for bullfighting broadcasts on Spain’s regional television channels, which has increased in recent years, especially in those Autonomous Communities governed by the Partido Popular and VOX.

Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis
Zongli Ye, Jiachen Lian, Xuanru Zhou, Jinming Zhang, Haodong Li, Shuhe Li, Chenxu Guo, Anaisha Das, Peter Park, Zoe Ezzes, Jet Vonk, Brittany Morin, Rian Bogley, Lisa Wauters, Zachary Miller, Maria Gorno-Tempini, Gopala Anumanchipalli
https://arxiv.org/abs/2…

Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis
Accurate alignment of dysfluent speech with intended text is crucial for automating the diagnosis of neurodegenerative speech disorders. Traditional methods often fail to model phoneme similarities effectively, limiting their performance. In this work, we propose Neural LCS, a novel approach for dysfluent text-text and speech-text alignment. Neural LCS addresses key challenges, including partial alignment and context-aware similarity mapping, by leveraging robust phoneme-level modeling. We eval…

South Sudan and Israel
are discussing a deal
to resettle Palestinians
from war-torn Gaza
in the troubled African nation,
three sources told Reuters
- a plan quickly dismissed as unacceptable by Palestinian leaders.
The sources, who have knowledge of the matter but spoke on condition of anonymity,
said no agreement had been reached but talks between South Sudan and Israel were ongoing.
The plan, if carried further,
would envisage pe…

In 2018, an #anonymous Trump administration official delivered a stark warning about the threat he said the president posed with his erratic behavior.
The author was later revealed to be #Miles #Taylor.
When Trump returned…

Miles Taylor fights Trump’s order targeting him, calling it ‘an attack on free speech’
In 2018, an anonymous Trump administration official delivered a stark warning about the threat he said the president posed with his erratic behavior. The author was later revealed to be Miles Taylor. When Trump returned to office, he claimed Taylor’s actions could be treasonous and ordered DHS and other agencies to launch an investigation. Taylor joined Amna Nawaz to discuss his legal response.

VoxATtack: A Multimodal Attack on Voice Anonymization Systems
Ahmad Aloradi, \"Unal Ege Gaznepoglu, Emanu\"el A. P. Habets, Daniel Tenbrinck
https://arxiv.org/abs/2507.12081

VoxATtack: A Multimodal Attack on Voice Anonymization Systems
Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because these linguistic cues remain intact, they can be exploited to identify semantic speech patterns associated with specific speakers. In this work, we present VoxATtack, a novel multimodal de-anonymization model that incorporates both acoustic and textual information to attack anonymization systems. While previous resear…