상세정보
학술지
Fast Offline Transformer-based End-to-end Automatic Speech Recognition for Real-world Applications
- 발행일
- 202206
- 출처
- ETRI Journal, v.44 no.3, pp.476-490
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 21HS3400, 다중 화자간 대화 음성인식 기술개발, 박전규
- 초록
- 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.
- KSP 제안 키워드
- Art performance, Beam Search, End to End(E2E), Limited resources, Real-world applications, Speech Database, automatic speech recognition(ASR), connectionist temporal classification(CTC), error rate, long sequence, state-of-The-Art
본 저작물은 공공누리 제4유형 : 출처표시 + 상업적 이용금지 + 변경금지 조건에 따라 이용할 수 있습니다.
