Martijn Bartelds
Scholar

Martijn Bartelds

Google Scholar ID: 6acanlUAAAAJ
Postdoctoral Scholar, Stanford University
Computational linguisticsLanguage variationSpeech technology
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
292
 
H-index
9
 
i10-index
9
 
Publications
20
 
Co-authors
5
list available
Contact
Emailbartelds@stanford.eduTwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
8 items
Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens
2026
Cited
0
"Sorry, I Didn't Catch That": How Speech Models Miss What Matters Most
2026
Cited
0
Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition
arXiv.org · 2026
Cited
0
False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
2025
Cited
0
The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
2025
Cited
0
OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
2025
Cited
0
BLAB: Brutally Long Audio Bench
2025
Cited
0
CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
2025
Cited
0
Resume (English only)
Academic Achievements
  • PhD thesis nominated for the University of Groningen's best thesis of 2023.
  • Published multiple high-impact papers, including:
  • - "OLMoASR: Open Models and Data for Training Robust Speech Recognition Models" (arXiv, 2025)
  • - "BLAB: Brutally Long Audio Bench" (arXiv, 2025)
  • - "CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition" (arXiv, 2025)
  • - "Constructing Datasets From Public Police Body Camera Footage" (ICASSP 2025)
  • - "ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets" (Interspeech 2024)
  • - "Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation" (ACL 2023)
  • - "Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions" (ComputEL-6, 2023)
  • Led or contributed to several open-source projects such as OLMoASR, CAVA, and BLAB.
Co-authors
5 total
Martijn Wieling
Martijn Wieling
Professor (by S.A.) of Low Saxon / Groningen Language and Culture, University of Groningen
Dan Jurafsky
Dan Jurafsky
Professor of Linguistics and Computer Science, Stanford University
Co-author 3
Co-author 3
Wietse de Vries
Wietse de Vries
Postdoc, University of Groningen
Mark Liberman
Mark Liberman
Professor, University of Pennsylvania