감정발화의 데이터베이스 구축과 음향 분석
Emotional Speech Database and the Acoustic Analysis of Emotional Speech
2
조회
0
다운로드
8
인용
0
참고문헌
키워드
초록
This paper aims to propose a method to induce emotional speech naturally and to carry out basic acoustic analyses of emotional speech. Previous research into emotional speech relied on the recordings of actors’ acted speech. Since actors’ emotional speech is often stereotyped, we established a method to help ordinary people to produce emotional speech relatively easily by using emotion inducing video clips edited from Korean films and dramas. 43 students and 20 actors and actresses participated in the recording. They were asked to read the subtitles embedded on the video clips while maintaining induced emotions. A test sentence, “Neo Nagiju ara? (Do you know Nagiju?)”, was included in the subtitles on the video clips. A perception test was conducted to choose top 50 natural sounding speech files of the test sentence for each emotion (i.e. anger, anxiety or neutral emotion). The result of this perception test shows that the proposed method was successful in inducing emotions naturally. The results of the acoustic analysis of the selected emotional utterances show that anger is realized with the highest pitch and biggest intensity and anxiety with the lowest pitch and weakest intensity. At the latter part of anxious speech, breathiness was observed.
Abstract
This paper aims to propose a method to induce emotional speech naturally and to carry out basic acoustic analyses of emotional speech. Previous research into emotional speech relied on the recordings of actors’ acted speech. Since actors’ emotional speech is often stereotyped, we established a method to help ordinary people to produce emotional speech relatively easily by using emotion inducing video clips edited from Korean films and dramas. 43 students and 20 actors and actresses participated in the recording. They were asked to read the subtitles embedded on the video clips while maintaining induced emotions. A test sentence, “Neo Nagiju ara? (Do you know Nagiju?)”, was included in the subtitles on the video clips. A perception test was conducted to choose top 50 natural sounding speech files of the test sentence for each emotion (i.e. anger, anxiety or neutral emotion). The result of this perception test shows that the proposed method was successful in inducing emotions naturally. The results of the acoustic analysis of the selected emotional utterances show that anger is realized with the highest pitch and biggest intensity and anxiety with the lowest pitch and weakest intensity. At the latter part of anxious speech, breathiness was observed.
참고문헌 (14)
- 감정발화 음성의 화자식별률 제고를 위한 개인 음성변이 연구(Ⅰ). 대검찰청 연구 결과 보고서, "이호영", 한국포렌직학회, ~ (2011)
- Banse, R., "Acoustic Profiles in Vocal Emotion Expression", Journal of Personality and Social Psychology, 70(3), pp.614~636 (1996)
- Bänziger, T., "The role of intonation in emotional expressions", Speech Communication, 46, pp.252~267 (2005)
- Bulut, M., "On the robustness of overall F0-only modifications to the perception of emotions in speech", Journal of the Acoustical Society of America, 123(6), pp.4547~4558 (2008)
- Campbell, N., "Databases of Emotional Speech", Proceedings of ISCA 2000, pp.34~38 (2000)
- Cosmides, L., "Invariances in the Acoustic Expression of Emotion During Speech", Journal of Experimental Psychology: Human Perception and Performance, 9, pp.864~881 (1983)
- Kuenzel, H., "Automatic Speaker Recognition of Identical Twins", International Journal of Speech, Language and the Law, 17(2), pp.251~277 (2010)
- Paeschke, A., "Prosodic Characteristics of Emotional Speech", Proceedings of ISCA ITRW on Speech and Emotion, pp.75~80 (2000)
- Scherer, K. R., "Vocal affect expression: A review and a model for future research", Psychological Bulletin, 99, pp.143~165 (1986)
- Scherer, K. R., "Vocal Communication of Emotions: A Review of Research Paradigms", Speech Communication, 40, pp.227~256 (2003)
- Scherer, K. R., "Emotion Inferences from Vocal Expression Correlate across Language and Cultures", Journal of Cross-Cultural Psychology, 32(1), pp.76~92 (2001)
- Waaramaa, Teija, "Perception of Emotional Valences and Activity Levels from Vowel Segments of Continuous Speech", Journal of Voice, 24(1), pp.30~38 (2010)
- Xu, Y., "Effects of tone and focus on the formation and alignment of f0 contours", Journal of Phonetics, 27, pp.55~105 (1999)
- 孫湳昊, "普通話聲調與邊界調音高特徵及其實現規則", 博士, pp.2006