collaborators

7 papers

eess.AS2026

Multimodal Speaker Verification as a Threat to Speaker Anonymization

Ashi Garg, Cristina Aggazzotti, Leibny Paola García-Perera +1

Most automatic speaker verification (ASV) systems operate on individual utterances, despite real-world interactions typically consisting of multiple utterances. As speech accumulat…

cs.CL2026

STEB: Style Text Embedding Benchmark

Rafael Rivera Soto, Anna Wegmann, Cristina Aggazzotti

While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their o…

cs.CL2026

CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data

Pedro Ortiz Suarez, Laurie Burchell, Catherine Arnett +94

Language identification (LID) is a fundamental step in curating multilingual corpora. However, LID models still perform poorly for many languages, especially on the noisy and heter…

cs.SD2026

Content Anonymization for Privacy in Long-form Audio

Cristina Aggazzotti, Ashi Garg, Zexin Cai +1

Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmarks such as the VoicePrivacy Challenge.…

cs.CL2026

The Impact of Automatic Speech Transcription on Speaker Attribution

Cristina Aggazzotti, Matthew Wiesner, Elizabeth Allyn Smith +1

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 especiall…

cs.CL2025

A stylometric analysis of speaker attribution from speech transcripts

Cristina Aggazzotti, Elizabeth Allyn Smith

Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications,…