AUTHOR=Li Haifang , Tang Chao , Yue Xin , Li Xu 

TITLE=Sentence-level consistency of conformer based pre-training distillation for Chinese speech recognition

JOURNAL=Frontiers in Communications and Networks

VOLUME=Volume 6 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/communications-and-networks/articles/10.3389/frcmn.2025.1662788

DOI=10.3389/frcmn.2025.1662788

ISSN=2673-530X

ABSTRACT=IntroductionWe address robustness and efficiency in Chinese automatic speech recognition (ASR), focusing on long-form broadcast speech where sentence-level semantic consistency is often lost.MethodsWe propose a Conformer-based framework that integrates sentence-level consistency with pre-training knowledge distillation. We also construct CH Broadcast ASR, a domain-specific Chinese corpus for the broadcast and television domain, and evaluate on AISHELL-1, AISHELL-3, and CH Broadcast ASR.ResultsThe proposed model consistently outperforms strong baselines (TDNN, DFSMN-T, TCN-Transformer), achieving CER = 3.3% on AISHELL-1, 3.7% on AISHELL-3, and 3.9% on CH Broadcast ASR, while reducing model size by >10%.DiscussionEnforcing sentence-level semantic alignment together with distillation improves robustness for long-form broadcast speech and enhances efficiency for real-time deployment.