Simon Berger, Larissa Kleppel, Ralf Schlüter · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31259 · open-access PDF
검색은 자동 언어 인식 (ASR) 시스템의 핵심 구성 요소이며 Hidden Markov Models (HMMs)를 기반으로하는 고전적인 ASR 모델링을 위해 깊이 연구되었습니다. 그러나 현재의 순서별 ASR 아키텍처에 대한 작업에서는 종종 외부 언어 모델 (LM)이없는 작은 고정 크기의 광선 검색으로 단순화됩니다.이 작업에서 우리는 서로 다른 절단 전략 및 LM 구성에서 Connectionist Temporal Classification (CTC) 및 신경 변환기 모델에 대한 검색 공간 복잡성과 효율성에 대한 비교 분석을 제시합니다.
Machine translation (Meta M2M100); the English original follows.
Search is a central component of Automatic Speech Recognition (ASR) systems and has been deeply investigated for classical ASR modeling based on Hidden Markov Models (HMMs). However, in work on current sequence-to-sequence ASR architectures it is often simplified to a small fixed-size beam search without external Language Model (LM). In this work, we present a comparative analysis of search space complexity and efficiency for Connectionist Temporal Classification (CTC) and neural transducer models under different pruning strategies and LM configurations. We show that these end-to-end (E2E) mod
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31259, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange