IKFST: IOO and KOO Algorithms for Accelerated and Precise WFST-based End-to-End Automatic Speech Recognition
Abstract
End-to-end automatic speech recognition has become the dominant paradigm in both academia and industry. To enhance recognition performance, the Weighted Finite-State Transducer (WFST) is widely adopted to integrate acoustic and language models through static graph composition, providing robust decoding and effective error correction. However, WFST decoding relies on a frame-by-frame autoregressive search over CTC posterior probabilities, which severely limits inference efficiency. Motivated by establishing a more principled compatibility between WFST decoding and CTC modeling, we systematically study the two fundamental components of CTC outputs, namely blank and non-blank frames, and identify a key insight: blank frames primarily encode positional information, while non-blank frames carry semantic content. Building on this observation, we introduce Keep-Only-One and Insert-Only-One, two decoding algorithms that explicitly exploit the structural roles of blank and non-blank frames to achieve significantly faster WFST-based inference without compromising recognition accuracy. Experiments on large-scale in-house, AISHELL-1, and LibriSpeech datasets demonstrate state-of-the-art recognition accuracy with substantially reduced decoding latency, enabling truly efficient and high-performance WFST decoding in modern speech recognition systems.
Cite
@article{arxiv.2601.00160,
title = {IKFST: IOO and KOO Algorithms for Accelerated and Precise WFST-based End-to-End Automatic Speech Recognition},
author = {Zhuoran Zhuang and Ye Chen and Chao Luo and Tian-Hao Zhang and Xuewei Zhang and Jian Ma and Jiatong Shi and Wei Zhang},
journal= {arXiv preprint arXiv:2601.00160},
year = {2026}
}