한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

모바일 환경을 고려한 규칙기반 음성인식 오류교정

Rule-based Speech Recognition Error Correction for Mobile Environment

  • 김진형 (상명대학교 디지털미디어학부) ;
  • 박소영 (상명대학교 게임모바일콘텐츠학과)
  • 투고 : 2012.06.12
  • 심사 : 2012.08.08
  • 발행 : 2012.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 모바일 환경에서 음성인식한 결과에 포함된 오류를 교정하는 규칙기반 접근방법을 제안한다. 제안하는 방법은 처리시간이나 메모리에 제약을 받는 모바일 환경을 고려하여 다음과 같이 구성된다. 오류 교정 속도를 최소화하기 위해서, 음절 해체 및 조합 과정이나 형태소 분석 등의 처리를 줄이고, 최장일치 규칙 선택기준을 바탕으로 오류 발생 추정 지점에서 교정 후보도 하나만 생성한다. 제안하는 방법은 메모리를 효율적으로 사용하기 위해서, 어절사전이나 형태소분석기를 사용하지 않고, 규칙도 유형별로 따로 구분하지 않고 통합하여 저장한다. 제안하는 방법은 모델의 수정 및 유지보수가 용이하도록, 오류교정규칙을 학습말뭉치에서 자동으로 추출하여 구축한다. 실험결과 제안하는 방법은 음성인식 결과에 대하여 정확률을 5.27% 정도 재현율을 5.60% 정도 개선하였다.

In this paper, we propose a rule-based model to correct errors in a speech recognition result in the mobile device environment. The proposed model considers the mobile device environment with limited resources such as processing time and memory, as follows. In order to minimize the error correction processing time, the proposed model removes some processing steps such as morphological analysis and the composition and decomposition of syllable. Also, the proposed model utilizes the longest match rule selection method to generate one error correction candidate per point, assumed that an error occurs. For the purpose of deploying memory resource, the proposed model uses neither the Eojeol dictionary nor the morphological analyzer, and stores a combined rule list without any classification. Considering the modification and maintenance of the proposed model, the error correction rules are automatically extracted from a training corpus. Experimental results show that the proposed model improves 5.27% on the precision and 5.60% on the recall based on Eojoel unit for the speech recognition result.

키워드

참고문헌

  1. Dong-Hee Lim, Seung-Shik Kang, Du-Seong Chang, "Word Spacing Error Correction for the Postprocessing of Speech Recognition", Proceedings of Korea Computer Congress, Vol. 33, No. 1, pp. 25-27, Jun. 2006.
  2. Myung-Won Kim, Young-Jin Kim, Eun-Ju Kim, "User Adaptive Post-Processing in Speech Recognition for Mobile Devices", Journal of KIISE, Vol. 13, No. 5, pp. 338-342, Oct. 2007.
  3. Do-Gil Lee, Sang-Zoo Lee, Heui-Seok Lim, Hae-Chang Rim, "Two Statistical Models for Automatic Word Spacing of Korean Sentences", Journal of KIISE : Software and Applications, Vol. 30, No. 4, pp. 358-371, Apr. 2003.
  4. Jeung-Hyun Byun, So-Young Park, Seung-Wook Lee, Hae-Chang Rim, "Three-Phase Text Error Correction Model for Korean SMS Messages", IEICE TRANSACTIONS on Information and Systems, Vol. E92-D, No. 5 pp. 1213-1217, May. 2009. https://doi.org/10.1587/transinf.E92.D.1213
  5. Hun-Gjong Noh, Jeong-Wong Cha, Geun-Bae Lee, "A joint statistical model for word spacing and spelling error correction", Journal of KIISE : Software and Applications, Vol. 34, No. 2, pp. 131-139, Feb. 2007.
  6. So-Young Park, Jeung-hyun Byun, Hae-Chang Rim, Do-Gil Lee, Heuiseok Lim, "Natural language-based user interface for mobile devices with limited resources", IEEE Transactions on Consumer Electronics, Vol. 56, No. 4, pp. 2086-2092, Nov. 2010. https://doi.org/10.1109/TCE.2010.5681076
  7. AiTi Aw, Min Zhang, Juan Xiao, Jian Su, "A Phrase-Based Statistical Model for SMS Text Normalization". Proceedings of the COLING/ACL on Main Conference Poster Sessions, pp. 33-40, Jul. 2006.
  8. Eric Mays, Fred J. Damerau and Robert L. Mercer "Context Based Spelling Correction", Information Processing and Management, Vol. 27, No. 5, pp. 517-522, 1991. https://doi.org/10.1016/0306-4573(91)90066-U
  9. Bong-Rae Park, Hae-Chang Rim, "Recognizing Unknown Words and Correcting Spelling Errors as Preprocessing for Korean Information Processing System", Journal of Information Processing Systems, Vol. 5, No. 10, pp. 2591-2599, Oct. 1998.
  10. Eric Brill, "Transformation-based error-driven learning and natural language processing: A case study in part-of-speech tagging", Computational Linguistics, Vol. 21, No. 4, pp. 543-565, Dec. 1995
  11. Young-Sin Lee, Young-Ja Park, Man-Suk Song, "Spelling Correction in Korean Using the 'Eojeol' Generation Dictionary", The KIPS Transactions : Part B, Vol. 8B No. 1, pp. 98-104, Feb. 2001.
  12. Masaaki Nagata, "Context-Based Spelling Correction for Japanese OCR", Proceedings of the COLING, pp. 806-811, Aug. 1996.
  13. Jin-Hee Yoo, Jong-Hyeok Lee, Geun-Bae Lee, "Post - Processing for Character Recognition Using Morphological Analysis and Linguistic Evaluation", Journal of KIISE, Vol. 22, No. 6, pp. 880-891, Jun. 1995.
  14. Won-Il Lee, Nam-Hee Hong, Jong-Hyuk Lee, Geun-Bae Lee, "Design and Implementation of Korean Spelling Corrector based on Morphological Analysis and Binary N-gram Method", Journal of KIISE Vol. 20, No. 1, pp. 813-816, Apr. 1993.
  15. Jeung-Hyun Byun, "Automatic Extraction of Spelling Correction Rule using Corrected Corpus", Master Thesis, Korea University, Feb. 2008
  16. Han-Kyu Lim, Ung-Mo Kim, "A Spelling Correction System Based on Statistical Data of Spelling Errors", Journal of information Processing Systems, Vol. 2, No. 6, pp. 839-846, Nov. 1995.
  17. Han-Min Jung, Geun-Bae Lee, Jong-Hyeok Lee. "An Implementation of Neuro-Fuzzy Korean Spelling Corrector Using Keyboard Arrangement Characteristics", Proceedings of the 5th Annual Conference on Human and Cognitive Language Technology, pp. 317-328, Oct. 1993.
  18. Kwang-Seob Shim, Jae-Hyung Yang, "High Speed Korean Morphological Analysis based on Adjacency Condition Check", Journal of KIISE : Software and Application, Vol. 31 No. 1, pp. 89-99, Jan. 2004.

피인용 문헌

  1. 음성 합성 시스템의 품질 향상을 위한 한국어 문장 기호 전처리 시스템 vol.20, pp.2, 2012, https://doi.org/10.9708/jksci.2015.20.2.149