Imagen de Portada

Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Herron, Felix, Rossato, Solange, Allauzen, Alexandre, Portet, François
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Responsible Benchmarking of Fairness for Automatic Speech Recognition
por: Herron, Felix, et al.
Publicado: (2026)

Where Do Self-Supervised Speech Models Become Unfair?
por: Herron, Felix, et al.
Publicado: (2026)

LLM-based phoneme-to-grapheme for phoneme-based speech recognition
por: Ma, Te, et al.
Publicado: (2025)

Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
por: Dong, Lukuang, et al.
Publicado: (2026)

Emergent morpho-phonological representations in self-supervised speech models
por: Gauthier, Jon, et al.
Publicado: (2025)

Polynomial Mixing for Efficient Self-supervised Speech Encoders
por: Feillet, Eva, et al.
Publicado: (2026)

Sustainable self-supervised learning for speech representations
por: Lugo, Luis, et al.
Publicado: (2024)

emg2speech: Synthesizing speech from electromyography using self-supervised speech models
por: Gowda, Harshavardhana T., et al.
Publicado: (2025)

Probing self-attention in self-supervised speech models for cross-linguistic differences
por: Gopinath, Sai, et al.
Publicado: (2024)

Word stress in self-supervised speech models: A cross-linguistic comparison
por: Bentum, Martijn, et al.
Publicado: (2025)

Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations
por: Mohamed, Mukhtar, et al.
Publicado: (2024)

Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech
por: Garg, Abhinav, et al.
Publicado: (2024)

PRODIS -- a speech database and a phoneme-based language model for the study of predictability effects in Polish
por: Malisz, Zofia, et al.
Publicado: (2024)

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
por: Méloux, Maxime, et al.
Publicado: (2025)

Employing self-supervised learning models for cross-linguistic child speech maturity classification
por: Zhang, Theo, et al.
Publicado: (2025)

LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
por: Parcollet, Titouan, et al.
Publicado: (2023)

Can GPT models Follow Human Summarization Guidelines? A Study for Targeted Communication Goals
por: Zhou, Yongxin, et al.
Publicado: (2023)

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation
por: Duong, Song, et al.
Publicado: (2025)

Tracking the emergence of linguistic structure in self-supervised models learning from speech
por: Kloots, Marianne de Heer, et al.
Publicado: (2026)

AfriHuBERT: A self-supervised speech representation model for African languages
por: Alabi, Jesujoba O., et al.
Publicado: (2024)

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
por: Fujita, Kenichi, et al.
Publicado: (2024)

Prominence-aware automatic speech recognition for conversational speech
por: Linke, Julian, et al.
Publicado: (2025)

Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition
por: Triantafyllopoulos, Andreas, et al.
Publicado: (2024)

Automated Clinical Report Generation for Remote Cognitive Remediation: Comparing Knowledge-Engineered Templates and LLMs in Low-Resource Settings
por: Zhou, Yongxin, et al.
Publicado: (2026)

PSentScore: Evaluating Sentiment Polarity in Dialogue Summarization
por: Zhou, Yongxin, et al.
Publicado: (2023)

Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models
por: Gubian, Michele, et al.
Publicado: (2025)

Introduction to speech recognition
por: Dauphin, Gabriel
Publicado: (2024)

Do self-supervised speech and language models extract similar representations as human brain?
por: Chen, Peili, et al.
Publicado: (2023)

Improving child speech recognition with augmented child-like speech
por: Zhang, Yuanyuan, et al.
Publicado: (2024)

Cropping outperforms dropout as an augmentation strategy for self-supervised training of text embeddings
por: González-Márquez, Rita, et al.
Publicado: (2025)

Tutorial: $φ$-Transductions in OpenFst via the Gallic Semiring
por: Cognetta, Marco, et al.
Publicado: (2025)

A* shortest string decoding for non-idempotent semirings
por: Gorman, Kyle, et al.
Publicado: (2022)

Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance
por: Ueda, Kentaro, et al.
Publicado: (2025)

MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies
por: Ha, Huy Hoang, et al.
Publicado: (2026)

Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
por: Méloux, Maxime, et al.
Publicado: (2025)

Exploring the limits of decoder-only models trained on public speech recognition corpora
por: Gupta, Ankit, et al.
Publicado: (2024)

What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
por: Zhang, Xinhao, et al.
Publicado: (2026)

A low latency attention module for streaming self-supervised speech representation learning
por: Ma, Jianbo, et al.
Publicado: (2023)

Exploring Precision and Recall to assess the quality and diversity of LLMs
por: Bronnec, Florian Le, et al.
Publicado: (2024)

Are LLM-based methods good enough for detecting unfair terms of service?
por: Frasheri, Mirgita, et al.
Publicado: (2024)