본문 바로가기
KERD
논문KCI 등재

독일어 감정음성에서 추출한 포먼트의 분석 및 감정인식 시스템과 음성인식 시스템에 대한 음향적 의미

An Analysis of Formants Extracted from Emotional Speech and Acoustical Implications for the Emotion Recognition System and Speech Recognition System

이서배
한국음성학회 (The Korean Society of Speech Sciences)|2011.03|말소리와 음성과학 (Phonetics and Speech Sciences)|제3권 제1호|pp. 45-50

1

조회

0

다운로드

6

인용

0

참고문헌

키워드

emotionvowelformantspeech
주제분류학제간연구

초록

Formant structure of speech associated with five different emotions (anger, fear, happiness, neutral, sadness) was analysed. Acoustic separability of vowels (or emotions) associated with a specific emotion (or vowel) was estimated using F-ratio. According to the results, neutral showed the highest separability of vowels followed by anger, happiness, fear, and sadness in descending order. Vowel /A/ showed the highest separability of emotions followed by /U/, /O/, /I/ and /E/ in descending order. The acoustic results were interpreted and explained in the context of previous articulatory and perceptual studies. Suggestions for the performance improvement of an automatic emotion recognition system and automatic speech recognition system were made.

Abstract

Formant structure of speech associated with five different emotions (anger, fear, happiness, neutral, sadness) was analysed. Acoustic separability of vowels (or emotions) associated with a specific emotion (or vowel) was estimated using F-ratio. According to the results, neutral showed the highest separability of vowels followed by anger, happiness, fear, and sadness in descending order. Vowel /A/ showed the highest separability of emotions followed by /U/, /O/, /I/ and /E/ in descending order. The acoustic results were interpreted and explained in the context of previous articulatory and perceptual studies. Suggestions for the performance improvement of an automatic emotion recognition system and automatic speech recognition system were made.

참고문헌 (25)

  1. Anderson, E, "A Grammar of Iconism" (1998), Fairleigh Dickinson University Press
  2. Athanaselis, T, "ASR for emotional speech: clarifying the issues and enhancing performance", Neural Networks, 18(4), pp.437~444 (2005)
  3. Belhumeur, P, "Eigenfaces vs. fisherfaces: recognition using class specific linear projection", IEEE Transaction Pattern Analysis and Machine Intelligence, 19(7), pp.711~720 (1997)
  4. "Praat: doing phonetics by computer (Version 5.1.05)" (2009)[URL]
  5. Burkhardt, F, "A database of German emotional speech", Proc. Interspeech 2005, pp.1517~1520 (2005)
  6. Darch, J, "Predicting formant frequencies from MFCC vectors", ICASSP, pp.941~944 (2005)
  7. Darch, J, "MAP prediction of formant frequencies and voicing class from MFCC vectors in noise", Speech Communication In Robustness Issues for Conversational Interaction, 48(11), pp.1556~1572 (2006)
  8. Fant, G, "Acoustic Theory of Speech Production(second printing)" (1970), de Gruyter Mouton
  9. Fisher, R. A, "The use of multiple measurements in taxonomic problems", Annals of Eugenics, 7, pp.179~188 (1936)
  10. Fragopanagos, N, "Emotion recognition in human-computer interaction", Neural Networks, 18(4), pp.389~405 (2005)
  11. Goudbeek, M, "Emotions and articulatory precision", Proceedings of Interspeech 2008, pp.317~ (2008)
  12. Goudbeek, M, "Emotion dimensions and formant position", Proceedings of Interspeech 2009, pp.1575~1578 (2009)
  13. Lee, S, "An articulatory study of emotional speech production", Proceedings of Interspeech 2005, pp.497~500 (2005)
  14. Noyes, J, "Speech recognition in adverse environments: The role of human mediation", ESCA, 1995, 17~20
  15. Rose, P, "Differences and distinguishability in the acoustic characteristics of hello in voices of similar sounding speakers: a forensic phonetic investigation", Australian Review of Applied Linguistics, 22(1), pp.1~42 (1999)
  16. Sambur, M, "Selection of acoustic features for speaker identification", IEEE Transactions on Acoustics, Speech, and Signal Processing, 23(2), pp.176~182 (1975)
  17. Scherer, K, "Vocal affect expression: A review and a model for future research", Psychological Bulletin, 99(2), pp.143~165 (1986)
  18. Thomson, D, "Ten case studies of the effect of field conditions on speech recognition errors", Proceedings of the IEEE ASRU Workshop, Santa Barbara, pp.511~518 (1997)
  19. Tsur, R, "What Makes Sound Patterns Expressive: The Poetic Mode of Speech-Perception" (1992), Duke University Press
  20. Waaramaa T, "Monopitched expression of emotions in different vowels", Folia Phoniatr Logop, 60, pp.249~255 (2008)
  21. Wakita, H, "Normalization of vowels by vocal tract length and its application to vowel identification", IEEE Trans. ASSP, 25, pp.183~192 (1977)
  22. "SAMPA computer readable phonetic alphabet" (1997)[URL]
  23. Wolf, J, "Efficient acoustic parameters for speaker recognition", Journal of the Acoustical Society of America, 51(6), pp.2044~2056 (1972)
  24. Yingchun Y, "Frequency shifting for emotional speaker recognition, In Pattern Recognition", pp.305~318 (2009)
  25. Yildirim, S, "An acoustic study of emotions expressed in speech", ICSLP, 통권 : 1, pp.2193~2196 (2004)

관련 논문AI추천

억양의 근접복사 유형화를 이용한 감정음성의 음향분석이서배한국음성학회 · 말소리와 음성과학2014 · 제6권 제3호감정 인식을 위한 음성 특징 도출권철홍, 김근호, 김종열, 송승규, 장준수한국음성학회 · 말소리와 음성과학2012 · 제4권 제2호영어 감정발화와 중립발화 간의 운율거리를 이용한 감정발화 분석이서배한국음성학회 · 말소리와 음성과학2020 · 제12권 제3호모음 공간의 재해석박한상사단법인 한국언어학회 · 언어학2024 · 제99호한국어 감정 음성에서 모멜로 추출한 피치 곡선 연구이서배한국언어과학회 · 언어과학2018 · 제25권 제3호감정발화의 데이터베이스 구축과 음향 분석손남호, 이호영, 황효성사단법인 한국언어학회 · 언어학2015 · 제72호

이 간행물의 다른 논문 (15건)

영어의 강음절(강세 음절)과 한국어 화자의 단어 분절남기춘, 김선미pp. 3-14한국인 영어 학습자의 어말 폐쇄음과 선행 모음 길이의 상관관계 연구김지은pp. 15-22미국인 아동이 발음한 영어모음의 포먼트 궤적양병곤pp. 23-34억양이 과장된 원어민 발화를 통한 영어 억양 교육과 평가윤규철pp. 35-43The Interlanguage Speech Intelligibility Benefit for Listeners (ISIB-L): The Case of English Liquids이주경, Xiaojiao Xuepp. 51-65
원문 보기