Special section: processing of semantic information

A Natural Language Dialogue System for Impression–based Music Retrieval

Tadahiko Kumamoto

National Institute of Information and Communications Technology, Hikaridai 3–5, Kansai Science City, Kyoto 619–0289, Japan. (email: kuma@nict.go.jp).

Manuscript received November 4, 2009.
Manuscript accepted for publication May 31, 2010.

Abstract

Impression–based music retrieval is the best way to find pieces of music that suit the preferences, senses, or mental states of users. A natural language interface (NLI) is more useful and effective than a graphical user interface for impression–based music retrieval since an NLI interprets users' spontaneous input sentences to represent musical impressions and generates query vectors for music retrieval. Existing impression–based music retrieval systems, however, have no dialogue capabilities for modifying the most recently used query vector. We evaluated a natural language dialogue system we developed that deals not only with 164 impression words but also with 14 comparative expressions, such as "a little more" and "more and more," and, if necessary, modifies the most recently used query vector through a dialogue. We also evaluated performance using 35 participants to determine the effectiveness of our dialogue system.

Key words: Music retrieval, impression–based, natural langauge dialogue.

DESCARGAR ARTÍCULO EN FORMATO PDF

REFERENCES

[1] Ghias, A., Logan, J., Chamberlin, D., and Smith, B.: Query By Humming – Musical Information Retrieval in an Audio Database. In Proc. of ACM Int. Multimedia Conf., San Francisco, USA (1995)        [ Links ]

[2] Blackburn, S. G., and De Roure, D. C.: A Tool for Content based Navigation of Music. In Proc. 6th ACM Int. Multimedia Conf., Bristol, UK (1998) 361–368        [ Links ]

[3] Sonoda, T., Goto, M., and Muraoka, Y.: A WWW–based Melody Retrieval System. In Proc. Int. Computer Music Conf., Michigan, USA (1998) 349–352        [ Links ]

[4] Kosugi, N., Nagata, H., and Nakanishi, T.: Query–by–Humming on Internet. In Proc. Int. Conf. on Database and Expert Systems Applications (2003) 589–600        [ Links ]

[5] Tsuji, Y., Hoshi, M., and Ohmori, T.: Local Pattern of a Melody and Its Applications to Retrieval by Sensitivity Words. Technical Report of IEICE of Japan, Vol. SP96–124 (1997) 17–24        [ Links ]

[6] Sato, A., Ogawa, J., and Kitakami, H.: An Impression–based Retrieval System of Music Collection. In Proc. of 4th Int. Conf. on Knowledge–Based Intelligent System and Allied Technologies, Brighton, U.K. (2000) 856–859        [ Links ]

[7] Ikezoe, T., Kajikawa, Y., and Nomura, Y.: Music Database Retrieval System with Sensitivity Words Using Music Sensitivity Space. Trans. IPS of Japan, Vol. 42, No. 12 (2001) 3201–3212         [ Links ]

[8] Omae, H., Ishibashi, N., Kiyoki, Y., and Anzai, Y.: An Automatic Metadata Creation Method for Music with Multiple Musical Instruments. Technical Report of IPS of Japan, Vol. 2001–DBS–125, No. 84 (2001) 145–152        [ Links ]

[9] Kumamoto, T., and Ohta, K.: A Query by Musical Impression System using N–gram Based Features. In Proc. IEEE Conference on Cybernetics and Intelligent Systems (2004) 992–997        [ Links ]

[10] Kumamoto, T.: Design and Implementation of Natural Language Interface for Impression–based Music–retrieval Systems. Lecture Notes in Artificial Intelligence, Vol. 3214, Springer–Verlag, Berlin Heidelbelg New York (2004) 139–147        [ Links ]

[11] Kumamoto, T., and Ohta, K.: Design and Development of Natural Language Interface for an Impression–based Music Retrieval System. Technical Report of IPS of Japan, Vol. 2003–NL–153, No. 13 (2003) 97–104        [ Links ]

[12] Harada, S., Itoh, Y., and Nakatani, H.: Interactive Image Retrieval by Natural Language. Optical Engineering, Vol. 36, No. 12 (1997) 3281–3287        [ Links ]

[13] Ohno S., and Hamanishi, M.: Ruigo–Kokugo–Jiten. Kadokawa Shoten Publishing Co.,Ltd., Tokyo, Japan (1985)         [ Links ]

[14] Kan, T.: Multivariate Statistical Analysis. Gendai–Sugakusha, Kyoto, Japan (1996)        [ Links ]

[15] Kurohashi, S., and Nagao, M.: Manual for Japanese Morphological Analysis System JUMAN Version 3.61. http://pine.kuee.kyoto–u.ac.jp/nl–resource/juman.html (1999)        [ Links ]

[16] Taniguchi, T.: Music and Affection. Kitaooji Syobo Press, Kyoto, Japan (1998)        [ Links ]