Optimal Turkish Subword Strategies at Scale: Systematic Evaluation of Data, Vocabulary, Morphology Interplay
Paper • 2602.06942 • Published • 3
Duygu Altinok PRO
BayanDuygu
AI & ML interests
Deep learning for speech and language/ Multilingual speech recognition/
Blending morphology into NLP pipelines especially speech
Recent Activity
updated a collection 2 days ago
Multilingual Audio-Text LT Test Sets updated a collection 3 days ago
Multilingual Audio-Text LT Test Sets updated a collection 3 days ago
Multilingual Audio-Text LT Test SetsOrganizations
submitted a
paper to Daily Papers 6 months ago
submitted a
paper to Daily Papers 8 months ago
authored 7
papers 8 months ago
Smooth Operators: LLMs Translating Imperfect Hints into Disfluency-Rich Transcripts
Paper • 2506.18510 • Published
Whispering Context: Distilling Syntax and Semantics for Long Speech Transcripts
Paper • 2508.13376 • Published
Mind the Gap: Entity-Preserved Context-Aware ASR Structured Transcriptions
Paper • 2506.22858 • Published
Boosting CTC-Based ASR Using LLM-Based Intermediate Loss Regularization
Paper • 2506.22846 • Published
D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models
Paper • 2405.04170 • Published
DEMorphy, German Language Morphological Analyzer
Paper • 1803.00902 • Published
Towards Turkish ASR: Anatomy of a rule-based Turkish g2p
Paper • 1601.03783 • Published