What Do Compressed Deep Neural Networks Forget?
Paper • 1911.05248 • Published
Awesome Speech Fairness
Papers, datasets, and models on bias and fairness in speech AI. Companion to arXiv:2605.01597.
-
-
Sparsely Shared LoRA on Whisper for Child Speech Recognition
Paper • 2309.11756 • Published • 1 -
In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
Paper • 2505.14887 • Published • 2 -
Acoustic-based Gender Differentiation in Speech-aware Language Models
Paper • 2509.21125 • Published -
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Paper • 2004.07667 • Published -
FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
Paper • 2506.10747 • Published -
LEACE: Perfect linear concept erasure in closed form
Paper • 2306.03819 • Published • 2 -
SYN2REAL: Leveraging Task Arithmetic for Mitigating Synthetic-Real Discrepancies in ASR Domain Adaptation
Paper • 2406.02925 • Published • 2 -
ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languages
Paper • 2512.10967 • Published -
CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
Paper • 2502.01777 • Published -
MOS-Bias: From Hidden Gender Bias to Gender-Aware Speech Quality Assessment
Paper • 2603.10723 • Published • 1 -
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Paper • 2310.00274 • Published • 4 -
SpeechAlign: Aligning Speech Generation to Human Preferences
Paper • 2404.05600 • Published • 1 -
Fairness Through Awareness
Paper • 1104.3913 • Published -
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
Paper • 2604.17248 • Published -
The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages
Paper • 2505.20564 • Published • 1 -
This Thing Called Fairness: Disciplinary Confusion Realizing a Value in Technology
Paper • 1909.11869 • Published -
Common Voice: A Massively-Multilingual Speech Corpus
Paper • 1912.06670 • Published • 2 -
Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models
Paper • 2408.07665 • Published -
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Paper • 2510.08047 • Published • 8 -
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
Paper • 2505.16211 • Published • 18 -
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
Paper • 1901.09451 • Published -
AHELM: A Holistic Evaluation of Audio-Language Models
Paper • 2508.21376 • Published • 9 -
The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource Languages
Paper • 2502.15916 • Published • 1 -
EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition
Paper • 2506.04652 • Published • 1 -
Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems
Paper • 2509.13989 • Published • 3 -
StereoSet: Measuring stereotypical bias in pretrained language models
Paper • 2004.09456 • Published • 1 -
CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition
Paper • 2506.06071 • Published • 1 -
A Survey on Bias and Fairness in Machine Learning
Paper • 1908.09635 • Published -
Ethical and social risks of harm from Language Models
Paper • 2112.04359 • Published • 1 -
Can Model Compression Improve NLP Fairness
Paper • 2201.08542 • Published -
CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese
Paper • 2511.04139 • Published • 1 -
Activation Steering for Accent-Neutralized Zero-Shot Text-To-Speech
Paper • 2603.05977 • Published -
Preservation of Language Understanding Capabilities in Speech-aware Large Language Models
Paper • 2509.12171 • Published -
Towards measuring fairness in speech recognition: Fair-Speech dataset
Paper • 2408.12734 • Published -
Bias and Fairness in Large Language Models: A Survey
Paper • 2309.00770 • Published • 5 -
Mitigating Gender Bias in Natural Language Processing: Literature Review
Paper • 1906.08976 • Published -
Equality of Opportunity in Supervised Learning
Paper • 1610.02413 • Published -
A Contrastive Learning Approach to Mitigate Bias in Speech Models
Paper • 2406.14686 • Published -
Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations
Paper • 2602.01030 • Published -
Activation Steering for Accent Adaptation in Speech Foundation Models
Paper • 2603.05813 • Published -
Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction
Paper • 2210.05791 • Published -
mozilla-foundation/common_voice_17_0
Updated • 3.37k • 53 -
intronhealth/afrispeech-200
Updated • 2.31k • 41 -
zsayers/CORAAL
Updated • 8.45k • 4 -
b-brave/speech_disorders_voice
Viewer • Updated • 1.64k • 110 • 1 -
DynamicSuperb/StutteringDetection_SEP28k
Viewer • Updated • 1k • 33 -
DynamicSuperb/VoiceDisorderClassification_VOICED
Viewer • Updated • 208 • 16 • 1 -
google/fleurs
Viewer • Updated • 768k • 117k • 475 -
naijavoices/naijavoices-dataset
Viewer • Updated • 1.92M • 1.41k • 32