Fast offline transformer‐based end‐to‐end automatic speech recognition for real‐world applications. Issue 3 (8th December 2021)

• Record Type: Journal Article
• Authors: Oh, Yoo Rhee; Park, Kiyoung; Park, Jeon Gue
• Is Part Of: ETRI journal. Volume 44:Issue 3(2022)
• Page Start: 476
• Page End: 490
• Publication Date: 2021-12-08
• Subjects: connectionist temporal classification -- end‐to‐end -- speech recognition -- transformer; Telecommunication -- Periodicals; Electronics -- Periodicals; Electronics; Telecommunication; Periodicals; Periodicals; 621.38205
• DOI: 10.4218/etrij.2021-0106
• Languages: English
• ISSNs: 1225-6463

Abstract

Abstract: With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real‐world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly recognize a large speech database via a transformer‐based end‐to‐end model. Transformers have improved the state‐of‐the‐art performance in many fields. However, they are not easy to use for long sequences. In this study, various techniques to accelerate the recognition of real‐world speeches are proposed and tested, including decoding via multiple‐utterance‐batched beam search, detecting end of speech based on a connectionist temporal classification (CTC), restricting the CTC‐prefix score, and splitting long speeches into short segments. Experiments are conducted with the Librispeech dataset and the real‐world Korean ASR tasks to verify the proposed methods. From the experiments, the proposed system can convert 8 h of speeches spoken at real‐world meetings into text in less than 3 min with a 10.73% character error rate, which is 27.1% relatively lower than that of conventional systems.