Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR

arXiv:2606.24169 · cs.AI · Submitted 2026-06-23 · Read on arXiv

cs.AI

Submitted: 2026-06-23

Updated: 2026-09-13

Comments: Accepted at IEEE SLT 2026

Code: https://github.com/huggingface/open

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 15× in this paper · explained in 12 episodes
• Fine-Tuning — 13× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Scaling Laws — 5× in this paper · explained in 4 episodes
• Cross-lingual Transfer — 3× in this paper · explained in 2 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Transfer Learning — 3× in this paper · explained in 10 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Common Voice — 2× in this paper
• Representation Learning — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• 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
• Decode — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Low-Resource Languages — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Towards scalable efficient on-device ASR with transfer learning
• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
• Sequence Transduction with Recurrent Neural Networks
• Scaling Laws for Transfer
• NeMo: a toolkit for building AI applications using Neural Modules
• Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection