[논문]AI의 음성 디자인에서 고려해야 할 감성적 요소 및 국가별 음성 트랜드에 관한 연구 - 핀란드와 노르웨이의 전문가 인뎁스 인터뷰를 중심으로

남궁기찬

doi:10.15207/jkcs.2020.11.9.091

AI의 음성 디자인에서 고려해야 할 감성적 요소 및 국가별 음성 트랜드에 관한 연구 - 핀란드와 노르웨이의 전문가 인뎁스 인터뷰를 중심으로
Research on Emotional Factors and Voice Trend by Country to be considered in Designing AI's Voice - An analysis of interview with experts in Finland and Norway 원문보기

한국융합학회논문지 = Journal of the Korea Convergence Society, v.11 no.9, 2020년, pp.91 - 97

남궁기찬 (국민대학교 산학협력단)

초록
AI-Helper

사용자와의 인터랙션이 가능한 음성 기반의 인터페이스는 AI 기술의 발달에 따라 사용이 확대되고 있다. 하지만, 현재까지의 음성 기반 인터페이스에 대한 연구는 음성 인식의 정확성 향상 등 기술적인 연구들이 대부분이었다. 이렇다 보니, 대부분의 음성 기반 인터페이스의 목소리는 차별화된 감성을 제공하지 않으며 획일화되어 있다. 본 연구에서는 AI 인터페이스의 음성에 적합한 감성 요소를 더하는 것을 목적으로 한다. 이를 위해 음성 인터페이스 디자인에서 고려되어야 할 감성적 요소를 도출하였다. 또한, 국가별로 차이를 보이는 보이스 트렌드를 조사하였다. 본 연구를 위해 자국의 언어를 독립적으로 사용하는 핀란드와 노르웨이, 두 국가의 음성 산업 전문가들과 인터뷰를 진행하였다.

Abstract ▼ AI-Helper

Use of voice-based interfaces that can interact with users is increasing as AI technology develops. To date, however, most of the research on voice-based interfaces has been technical in nature, focused on areas such as improving the accuracy of speech recognition. Thus, the voice of most voice-based interfaces is uniform and does not provide users with differentiated sensibilities. The purpose of this study is to add a emotional factor suitable for the AI interface. To this end, we have derived emotional factors that should be considered in designing voice interface. In addition, we looked at voice trends that differed from country to country. For this study, we conducted interviews with voice industry experts from Finland and Norway, countries that use their own independent languages.

주제어

표/그림 (4)

표 Table 1. Experts who took part in the interview
표 Table 2. Emotional factors to be considered in designing AI's voice
표 Table 3. Three representative emotional factors derived by bottom-up classification method
표 Table 4. Voice trends by country

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

Therefore, this study seeks to derive emotional factors of judgment to select the voice of the voice-based interface from a user-centered design perspective and to determine whether there is a voice preference due to cultural differences in each country. To this end, we interviewed experts in the voice industry in Finland and Norway, as representatives of countries that use their own languages.

대상 데이터

Ten voice industry experts from Finland and Norway participated in the interview.
The interviews were conducted in May 2018 in Helsinki, Finland, and Oslo, Norway.

성능/효과

Second, the importance of these emotional factors may vary from country to country. According to our results, Trustworthy was the most important factor for designing voices in Finland, whereas Inviting was the most important factor for designing voices in Norway, where unique voices are important.
According to the survey, in Finland, Trustworthy had 46%, Dynamic, 28%, and Inviting, 26%, In Norway, Inviting received 40%, Trustworthy, 32%, and Dynamic, 28%. These results reflect Finland’s voice trend, which traditionally values low-pitched, reliable voices, and that of Norway, which values regional color and individuality of voice.
We asked voice industry experts from the two countries who participated in the interview about the importance of emotional factors to be considered in the design of voice used in voice interfaces in each of their languages. Experts responded to the importance of each of the three emotional factors, so that the sum of the three factors of Dynamic, Inviting, and Trustworthy was 100%. Through this survey, we derived the importance of and differences in emotional factors to be considered in the design of voice interfaces that consider voice trends in each country.
Third, when designing the voice of a voice-based interface, ensuring that it matches the purpose and context of the product seems to be more important than simply choosing a voice of a preferred gender. In Finland, the voice trend has traditionally favored low-to-middle pitched male voices, but experts stated that it was more important to choose a gender that fits the purpose and situation of the product’s use than this voice trend.

참고문헌 (17)

Homma, T., Obuchi, Y., Shima, K., Ikeshita, R., Kokubo, H. & Matsumoto, T. (2018). In-vehicle voice interface with improved utterance classification accuracy using off-the-shelf cloud speech recognizer. IEICE Transactions on Information and Systems, E101D(12), 3123-3137. DOI : 10.1587/transinf.2018EDK0001.
Scanion, P., Elliss, D. P. W. & Reilly, R. B. (2007). Using broad phonetic group experts for improved speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 15(3), 803-802. DOI : 10.1109/TASL.2006.885907.

상세보기
Ramirez, J., Segura, J. C., Gorriz, J. M. & Garcia, L. (2007). Improved voice activity detection using contextual multiple hypothesis testing for robust speech recognition. IEEE Transactions on Audio, Speech & Language Processing, 15(8), 2177-2189. DOI : 10.1109/TASL.2007.903937.

상세보기
Zolnay, A., Kocharov, D., Schluter, R. & Ney, H. (2007). Using multiple acoustic feature sets for speech recognition. Speech Communication, 49(6), 514-525. DOI : 10.1016/j.specom.2007.04.005.

상세보기
HeeEun, L. (2018). Why do voice-activated technologies sound female? Sound technology and gendered voice of digital voice assistants. Korean Journal of Communication & Information, 90, 126-153.

상세보기
Nguyen, Q. N., Ta, A. & Prybutok, V. (2019). An integrated model of voice-user interface continuance intention: The gender effect. International Journal of Human-Computer Interaction, 35(15), 1362-1377. DOI : 10.1080/10447318.2018.1525023.

상세보기
Mabanza, N. (2018, December). Gender influences on preference of pedagogical interface agents. Proceedings of the International Conference on Intelligent & Innovative Computing Applications , Plaine Magnien, Mauritius. DOI : 10.1109/ICONIC.2018.8601292.
Couper, M. P., Singer, E. & Tourangeau, R. (2004). Does voice matter? An interactive voice response (IVR) experiment. Journal of Official Statistics, 20(3), 551-570.

상세보기
Myles, J. F. (2013). Instrumentalizing voice: Applying Bahktin and Bourdieu to analyze interactive voice response service. Journal of Communication Inquiry, 37(3), 233-248. DOI : 10.1177/0196859913491765.

상세보기
Sydell, L. (2018). The push for a gender-neutral Siri. [Online]. www.npr.org/2018/07/09/627266501/the-push-for-agender- neutral-siri
Mehrabian, A. & Ferris, S. R. (1967). Inference of attitudes from nonverbal communication in two channels. Journal of Consulting Psychology, 31(3), 248-252.

상세보기
GwanHae, C., DongUk, C., BumJoo, L., Yeong, P. & YeonMan, J. (2017). A study on characterizing the voices of active announcers using voice analysis technology. The Journal of Korean Institute of Communication and Information Sciences, 42(7), 1422-1431. DOI : 10.7840/kics.2017.42.7.1422.

상세보기
Peterson, R. A., Cannito, M. P. & Brown, S. P. (1995). An exploratory investigation of voice characteristics and selling effectiveness. Journal of Personal Selling & Sales Management, 15(1), 1-15.

상세보기
Suzuki, H., Zen, H., Nankaku, Y., Miyajima, C., Tokuda, K. & Kitamura, T. (2003). Speech recognition using voice-characteristic-dependent acoustic models. Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing , Hong Kong, China. DOI : 10.1109/ICASSP.2003.1198887.
McCroskey, J. C. & Teven, J. J. (1999). Goodwill: A reexamination of the construct and its measurement. Communication Monographs, 66, 90-103. DOI : 10.1080/03637759909376464.

상세보기
McCroskey, J. C. & McCain, T. A. (1974). The measurement of interpersonal attraction. Speech Monographs, 41, 261-266. DOI : 10.1080/03637757409375845.

상세보기
Chad, E., Automn, E., Brett, S., Xialing, L. & Noelle, M. (2019). Evaluations of an artificial intelligence instructor's voice: Social identity theory in human-robot interactions. Computers in Human Behavior, 90, 357-362. DOI : 10.1016/j.chb.2018.08.027.

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format