Newest papers

A Systematic Comparison of Search Space Complexity and Efficiency for Time-Synchronous End-to-End ASR Models

Simon Berger, Larissa Kleppel, Ralf Schlüter · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31259 · open-access PDF

Spanish

La búsqueda es un componente central de los sistemas de reconocimiento automático de habla (ASR) y ha sido profundamente investigado para la modelización ASR clásica basada en modelos de Markov ocultos (HMMs). Sin embargo, en el trabajo sobre las arquitecturas actuales de ASR de secuencia a secuencia a menudo se simplifica a una pequeña búsqueda de rayos de tamaño fijo sin un modelo de lenguaje externo (LM). En este trabajo, presentamos un análisis comparativo de la complejidad del espacio de búsqueda y la eficiencia para la Clasificación Temporal Connectionista (CTC) y los modelos de transductores neuronales bajo diferentes estrategias de corte y configuraciones de LM. Mostramos que estos modos end-to-end (E2E)

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange