의도적인 공백 추가를 통한 음성 번역 정확도 향상 기법
A Method to Improve the Accuracy of Voice Translation by Adding Intentional Spaces
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Real-time voice translation systems receive a speaker s voice and translate their speech into another language. However, the meaning of a whole Korean sentence can be unintentionally changed because Korean words and syllables can be merged or divided by spaces. Therefore, the spaces between the speaker s sentences are occasionally not identified by the speech recognition system, so the translated sentences are sometimes incorrect. This paper presents a methodology to enhance the accuracy of voice translation by adding intentional spaces. An Android application was implemented using Google speech recognizer for Android and Google translator for the Web. The Google speech recognizer app for Android receives the speaker s voice sentences in Korean and shows the text results. Next, the proposed Android application adds spaces when the speaker speaks the dedicated word for the space. Finally, the modified Korean sentences are translated into English by Google translator for the Web. Using this method can enhance interpretation accuracy for translation systems.
Abstract
Real-time voice translation systems receive a speaker s voice and translate their speech into another language. However, the meaning of a whole Korean sentence can be unintentionally changed because Korean words and syllables can be merged or divided by spaces. Therefore, the spaces between the speaker s sentences are occasionally not identified by the speech recognition system, so the translated sentences are sometimes incorrect. This paper presents a methodology to enhance the accuracy of voice translation by adding intentional spaces. An Android application was implemented using Google speech recognizer for Android and Google translator for the Web. The Google speech recognizer app for Android receives the speaker s voice sentences in Korean and shows the text results. Next, the proposed Android application adds spaces when the speaker speaks the dedicated word for the space. Finally, the modified Korean sentences are translated into English by Google translator for the Web. Using this method can enhance interpretation accuracy for translation systems.
참고문헌 (13)
- 조규은, "인공지능 스피커(AI speaker) 사례 분석을 통한 고찰", 한국융합학회논문지, 9(8), pp.127~133 (2018), 한국융합학회[DOI]
- Kim S. D., "A Study on Speech Reco gnition System Using Continuous HMM", Proceedings of the Korea Multimedia Society Conference, 1998(12), pp.221~225 (1998)
- Eom H. Y., "A post processing of continuous speech recognition using N-gram words and sentence patterns", Proceedings of The Korean Institute of Information Scientists and Engineers, 27(1B), pp.324~326 (2000)
- 김진형, "모바일 환경을 고려한 규칙기반 음성인식 오류교정", 한국컴퓨터정보학회논문지, 17(10), pp.25~33 (2012), 한국컴퓨터정보학회
- Lim, D. H., "Word Spacing Error Correction for the Postprocessi ng of Speech Recognition", Proceedings of the Korean Information Science Society Conference, 2006(6), pp.25~27 (2006)
- Lee Y. J., "A Study of Preprocessing in the Speech Recogni tion System Using HMM Algorithm", Proceedings of The Institute of Electronics and Information Engineers, 1999(12), pp.668~671 (1999)
- 김영진, "모바일 기기를 위한 음성인식의 사용자 적응형 후처리", 정보과학회 컴퓨팅의 실제 논문지, 13(5), pp.338~342 (2007), 한국정보과학회
- 남기훈, "한글 단어의 음성 인식 처리에 관한 연구", 문화기술의 융합, 5(4), pp.407~412 (2019), 국제문화기술진흥원
- 장애리, "국내 기계 통번역의 발전 현황 분석: 한·중 언어 쌍을 중심으로", 번역학연구, 18(2), pp.171~206 (2017), 한국번역학회[DOI]
- Lee C. K., "English-to-Japanese Machine Translation Using Neural Networks", Journal of The Korean Institute of Information Scientists and Engineeres, 33(10), pp.48~52 (2015)
- "SpeechRecognizer"[URL]
- "Google 번역"[URL]