A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition

arXiv:2609.30160 · cs.CL, eess.AS · Submitted 2026-09-24 · Read on arXiv

cs.CL, eess.AS

Submitted: 2026-09-24

Updated: 2026-09-24

Code: https://github.com/saurabhk0317/wsasr_icassp27

Terminology

• Alignment — 10× in this paper · explained in 1 episode
• External Validation — 2× in this paper · explained in 2 episodes
• Omni-temporal Classification — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Pseudo-labeling — 1× in this paper · explained in 3 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Style-agnostic evaluation of ASR using multiple reference transcripts
• Towards Orthographically-Informed Evaluation of Speech Recognition Systems for Indian Languages
• WST: Weakly Supervised Transducer for Automatic Speech Recognition
• Differentiable Weighted Finite-State Transducers
• XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering