Image de couverture de livre

Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Conti, Lina, Fucci, Dennis, Gaido, Marco, Negri, Matteo, Wisniewski, Guillaume, Bentivogli, Luisa
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models
par: Conti, Lina, et autres
Publié: (2025)

Cross-Attention is Half Explanation in Speech-to-Text Models
par: Papi, Sara, et autres
Publié: (2025)

How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena
par: Gaido, Marco, et autres
Publié: (2024)

Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution
par: Fucci, Dennis, et autres
Publié: (2025)

Different Speech Translation Models Encode and Translate Speaker Gender Differently
par: Fucci, Dennis, et autres
Publié: (2025)

SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation
par: Papi, Sara, et autres
Publié: (2024)

How to Evaluate Speech Translation with Source-Aware Neural MT Metrics
par: Cettolo, Mauro, et autres
Publié: (2025)

StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection
par: Papi, Sara, et autres
Publié: (2024)

Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?
par: Gaido, Marco, et autres
Publié: (2024)

SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation
par: Djanibekov, Amirbek, et autres
Publié: (2026)

SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation
par: Fucci, Dennis, et autres
Publié: (2024)

A Prompt Response to the Demand for Automatic Gender-Neutral Translation
par: Savoldi, Beatrice, et autres
Publié: (2024)

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
par: Gaido, Marco, et autres
Publié: (2025)

FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian
par: Papi, Sara, et autres
Publié: (2025)

MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
par: Gaido, Marco, et autres
Publié: (2024)

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
par: Papi, Sara, et autres
Publié: (2026)

What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered Study
par: Savoldi, Beatrice, et autres
Publié: (2024)

When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP
par: Papi, Sara, et autres
Publié: (2023)

Better Late Than Never: Meta-Evaluation of Latency Metrics for Simultaneous Speech-to-Text Translation
par: Polák, Peter, et autres
Publié: (2025)

SBAAM! Eliminating Transcript Dependency in Automatic Subtitling
par: Gaido, Marco, et autres
Publié: (2024)

An LLM-as-a-judge Approach for Scalable Gender-Neutral Translation Evaluation
par: Piergentili, Andrea, et autres
Publié: (2025)

Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models
par: Piergentili, Andrea, et autres
Publié: (2024)

Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions
par: Savoldi, Beatrice, et autres
Publié: (2025)

Gender-Neutral Rewriting in Italian: Models, Approaches, and Trade-offs
par: Piergentili, Andrea, et autres
Publié: (2025)

The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence
par: Gaido, Marco, et autres
Publié: (2025)

How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not
par: Verdini, Francesco, et autres
Publié: (2024)

Assessing the Impact of Anisotropy in Neural Representations of Speech: A Case Study on Keyword Spotting
par: Wisniewski, Guillaume, et autres
Publié: (2025)

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
par: Papi, Sara, et autres
Publié: (2025)

Interpretable Coreference Resolution Evaluation Using Explicit Semantics
par: Gatti, Bruno, et autres
Publié: (2026)

Good, but not always Fair: An Evaluation of Gender Bias for three commercial Machine Translation Systems
par: Piazzolla, Silvia Alma, et autres
Publié: (2023)

FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity
par: Jourdan, Fanny, et autres
Publié: (2025)

Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs
par: Satish, Shree Harsha Bokkahalli, et autres
Publié: (2025)

Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context
par: Bartl, Marion, et autres
Publié: (2025)

Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs
par: Pearman, Edie, et autres
Publié: (2026)

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
par: Khan, Falaah Arif, et autres
Publié: (2025)

Gender Bias in Machine Translation and The Era of Large Language Models
par: Vanmassenhove, Eva
Publié: (2024)

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison
par: Lam, Tsz Kin, et autres
Publié: (2025)

Significance of Chain of Thought in Gender Bias Mitigation for English-Dravidian Machine Translation
par: Prahallad, Lavanya, et autres
Publié: (2024)

Beyond Semantics: Measuring Fine-Grained Emotion Preservation in Small Language Model-Based Machine Translation
par: Wisniewski, Dawid, et autres
Publié: (2026)

Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
par: Puhach, Dariia, et autres
Publié: (2025)