{"ID":2823360,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00160","arxiv_id":"2601.00160","title":"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.","short_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 er...","url_abs":"https://arxiv.org/abs/2601.00160","url_pdf":"https://arxiv.org/pdf/2601.00160v1","authors":"[\"Zhuoran Zhuang\",\"Ye Chen\",\"Chao Luo\",\"Tian-Hao Zhang\",\"Xuewei Zhang\",\"Jian Ma\",\"Jiatong Shi\",\"Wei Zhang\"]","published":"2026-01-01T01:33:06Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[\"Language Model\"]","has_code":false}