Pick of the week @fbk-mt.bsky.social: "Greater accessibility can amplify discrimination in generative AI" Gender bias in speech-based LLMs examined from multiple angles: a user survey, automatic bias measurement, and pitch manipulation experiments. arxiv.org/pdf/2603.22260

⏰ 4 days left to apply! 🎓 2 PhD positions still open: 🎯 Human-Centred Evaluation Frameworks for Multilingual Technologies ✨ Multimedia Personalization with Multimodal Large Language Models 📅 Deadline: 15 May 2026 🔗 Full details: iecs.unitn.it/education/ad...

@linaconti.bsky.social & @luisabentivogli.bsky.social are heading to #LREC2026 in Palma! They'll present two papers: 📄 Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation 📄 Phonetic-based Ranking for Improved Pseudo-Labelling in Low-Resource ASR See you there! 🌴

🎓 Come and join our group! 🎓 We offer 2 fully funded PhD positions: 🌍 Human-Centred Evaluation Frameworks for Multilingual Technologies (A6) 🤖 Multimedia Personalization with Multimodal Large Language Models (A7) ⏰ Deadline: 15 May 2026 🔗 Details: iecs.unitn.it/education/ad...

🎓 Today we attended the FBK PhD Day, and our amazing students presented their research lines: @apierg.bsky.social: gender-inclusive MT @linaconti.bsky.social: explainable speech translation @zhihangxie.bsky.social: long-form SpeechLLMs @uzumakidhairya.bsky.social: resource-efficient translation

💬 Pick of the week @fbk-mt.bsky.social: "Voice gender diversity: expression, perception and acoustics." A great review of gender-diverse voices. Covers acoustic properties, perception and the gap between self-expression of gender and how voices are heard. royalsocietypublishing.org/rsos/article...

Voice gender diversity: expression, perception and acoustics

Abstract. The voice is a key marker of gender identity, yet gender non-conforming speakers often diverge from binary vocal norms. This review synthesizes f

royalsocietypublishing.org

🎙️ Pick of the week @fbk-mt.bsky.social: "Lost in Transcription, Found in Distribution Shift" Traditional WER masks dangerous hallucinations in ASR systems. This paper proposes a dedicated metric to detect them. aclanthology.org/2025.finding...

🎉 Excited to share that my paper "The Unheard Alternative" was accepted to @blackboxnlp.bsky.social 2025! We introduce contrastive explanations for speech-to-text, identifying which audio features ST models use to assign a grammatical gender to the speaker. 📄 Preprint: arxiv.org/abs/2509.265...

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models

Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely regarded in explainable AI as more informative and interpretable th...

arxiv.org

Pick of the week @fbk-mt.bsky.social: "I Have No Mouth, and I Must Rhyme" 👄 a dive into how LLaMA develops internal phonetic representations despite never hearing speech. arxiv.org/pdf/2508.02527 #XAI #LLM #interpretability

Pick of the week @fbk-mt.bsky.social : arxiv.org/abs/2505.19606 by @cislmu.bsky.social @barbaraplank.bsky.social. XAI work on cross-lingual alignment in speech-to-text models that disentangles phonetics and semantics. Plus: their XAI insights yield actionable improvements for low-resource languages.

Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically

Cross-lingual alignment in pretrained language models (LMs) has enabled efficient transfer in text-based LMs. Such an alignment has also been observed in speech foundation models. However, it remains ...

arxiv.org

📢 Come and join our group! We offer a fully funded 3-year PhD position: 📔 Automatic translation with large multimodal models: iecs.unitn.it/education/ad... 📍Full details for application: iecs.unitn.it/education/ad... 📅 Deadline May 12, 2025 #NLProc #FBK

My pick of the week @fbk-mt.bsky.social: "MuPe Life Stories Dataset" introduces a spontaneous speech corpus that captures Brazilian diversity—across education levels, regional accents & age groups aclanthology.org/2025.coling-...

MuPe Life Stories Dataset: Spontaneous Speech in Brazilian Portuguese with a Case Study Evaluation on ASR Bias against Speakers Groups and Topic Modeling

Sidney Evaldo Leal, Arnaldo Candido Junior, Ricardo Marcacini, Edresson Casanova, Odilon Gonçalves, Anderson Silva Soares, Rodrigo Freitas Lima, Lucas Rafael Stefanel Gris, Sandra Aluísio. Proceedings...

aclanthology.org

While we look forward to a sunny Geneva, why wait to join the conversation? We’ve created a starter pack for our #GITT2025 friends! 🕵️ Follow researchers working on gender bias in MT 💬 Stay up to date and dive into the discussion! All info at sites.google.com/tilburgunive...