IEEE Research Papers

為表決心，要在這裡開一個分類來貼上和寫下今年FYP相關的文章。
也可以當作開發日／週／月誌，定期寫寫有關FYP的事情。
可能這對大家來說全無趣味，有興趣知道我在／將會做什麼的朋友請進吧。（笑）
如果真的有耐心看完以下Article的標題都會大約估到我的FYP是怎樣的Project了。

MIDI Related Papers/Articles in IEEE Xplore

Melody extraction on MIDI music files

Ozcan, G. Isikhan, C. Alpkocak, A.
Dept of Comput. Eng., Dokuz Eylul Univ., Izmir, Turkey

Abstract
In this study, we propose a new approach to extract monophonic melody from MIDI files and provide a comparison of existing methods. Our approach is based on the elimination of MIDI channels those do not contain melodic information. First, MIDI channels are clustered depending on pitch histogram. Afterwards, a channel is selected from each cluster as representative and remaining channels and their notes are removed. Finally, skyline algorithm is applied on the modified MIDI set to ensure accuracy of monophonic melody. We evaluated our approach within a test bed of MIDI files, composed of variable music styles. Both our approach and the results from experiments are presented in detail.

Motion curves in music: the statistical analysis of midi data

Das, M. Howard, D.M. Smith, S.L.
Dept. of Electron., York Univ., UK ;

This paper appears in: EUROMICRO Conference, 1999. Proceedings. 25th
Publication Date: 8-10 Sept. 1999
Volume: 2
On page(s): 13 – 19 vol.2
Number of Pages: 2 vol. (xxviii+530+478)
Meeting Date: 09/08/1999 – 09/10/1999
Location: Milan
Digital Object Identifier: 10.1109/EURMIC.1999.794756
Posted online: 2002-08-06 22:37:58.0
Abstract
This paper postulates that the analysis of multivariate MIDI data allows for the statistical analysis of motion in music. The paper deals with analysing the kinematic motion components within music, specifically music velocity (i.e. tempo) and music acceleration/deceleration (i.e. tempo change), based upon Truslit's definition of predominant up-down motion types (1938). Thus, the variables of music velocity and acceleration are mathematically defined and extracted from MIDI encodings. Analysis of music velocity indicates that the differing motion types have specific and consistent velocity profiles, and that these profiles can be expressed mathematically and analysed statistically. In particular the paper focuses on the open motion curve fit relating the open motion velocity curve to the beta distribution. Analysis of acceleration within music suggests that music acceleration is not constant in nature, implying that theories of linear velocity are inaccurate models. Hence, MIDI data analysis allows for the statistical exploration of musical kinematics

Polyphonic audio matching and alignment for music retrieval

Ning Hu Dannenberg, R.B. Tzanetakis, G.
Comput. Sci. Dept., Carnegie Mellon Univ., Pittsburgh, PA, USA

This paper appears in: Applications of Signal Processing to Audio and Acoustics, 2003 IEEE Workshop on.
Publication Date: 19-22 Oct. 2003
On page(s): 185 – 188
Number of Pages: xiii+238
ISSN:
Posted online: 2004-04-19 16:50:16.0
Abstract
We describe a method that aligns polyphonic audio recordings of music to symbolic score information in standard MIDI files without the difficult process of polyphonic transcription. By using this method, we can search through a MIDI database to find the MIDI file corresponding to a polyphonic audio recording.

Computer-aided composition from melodic contours and tabular constraints

Hung-Che Shen Chungnan Lee
Inst. of Comput. & Inf. Eng., Nat. Sun Yat-Sen Univ., Kaohsiung, Taiwan

This paper appears in: Web Delivering of Music, 2003. 2003 WEDELMUSIC. Proceedings. Third International Conference on
Publication Date: 15-17 Sept. 2003
On page(s): 101 – 104
Number of Pages: x+155
ISSN:
Digital Object Identifier: 10.1109/WDM.2003.1233881
Posted online: 2003-09-29 16:21:31.0
Abstract
The goal is to develop a framework of intelligent computer-aided composition based on melodic contours and tabular constraints. Melodic contour is derived from whistling input as a MIDI controller. Tabular constraint is a flexible representation for describing, processing, and synthesizing musical structure of MIDI format music. Based on a given melodic contour, there are two main areas of computer-aided composition to be treated: melody variation and harmonization. We develop a musical plan representation called tabular constraints to allow the interactive experimentation for those two composition activities. A set of transformation operators is available for automatic composition. We have demonstrated that the integration of melody transcription and tabular constraints can allow a user to easily explore his potential in melody creation and harmonization.

A dynamic programming approach to adaptive tatum assignment for rhythm transcription

Yang, A.C. Chew, E. Volk, A.
Viterbi Sch. of Eng., Southern California Univ., Los Angeles, CA, USA

This paper appears in: Multimedia, Seventh IEEE International Symposium on
Publication Date: 12-14 Dec. 2005
On page(s): 8 pp.
Number of Pages: CD-ROM
Digital Object Identifier: 10.1109/ISM.2005.5
Posted online: 2006-01-03 13:50:10.0
Abstract
We present a method for segmenting music with different grid levels in order to properly quantize note values in the transcription of music. This method can be used in automatic music transcription systems and music information retrieval systems to reduce a performance of a music piece to the printed or digital score. The system takes only the onset data of performed music from either MIDI or audio, and determine the best maximal grid level onto which to fit the note onsets. This maximal grid level, or tatum, is allowed to vary from section to section in a piece. We obtain the optimal segmentation of the piece using dynamic programming. We present results from an audio based performance of Milhaud's Botafogo, as well as several MIDI performances of the Rondo-Allegro from Beethoven's Pathetique. The results show a reduction of error compared to quantization based only on one global metric level, and promises to create rhythm transcriptions that are parsimonious and readable.

Content-based filtering system for music data

Iwahama, K. Hijikata, Y. Nishida, S.
Graduate Sch. of Eng. Sci., Osaka Univ., Japan

This paper appears in: Applications and the Internet Workshops, 2004. SAINT 2004 Workshops. 2004 International Symposium on
Publication Date: 26-30 Jan. 2004
On page(s): 480 – 487
Number of Pages: xxvi+719
ISSN:
Digital Object Identifier: 10.1109/SAINTW.2004.1268677
Posted online: 2004-03-03 16:16:17.0
Abstract
Recommender systems, which recommend appropriate information to users from enormous amount of information, are becoming popular. There are two methods to realize recommender systems. One is content-based filtering, and the other is collaborative filtering. Many systems using the former method deal with text data, and few systems deal with music data. This paper proposes a content-based filtering system that targets music data in MIDI format. First, we analyze characteristics of feature parameters about music data in MIDI format. Then we propose a filtering method based on the above feature parameters. Finally, we build a prototype system with standard technology of the Internet.

Progress towards recognizing and classifying beautiful music with computers – MIDI-encoded music and the Zipf-Mandelbrot law

Manaris, B. Purewal, T. McCormick, C.
Coll. of Charleston, SC, USA;

This paper appears in: SoutheastCon, 2002. Proceedings IEEE
Publication Date: 5-7 April 2002
On page(s): 52 – 57
Number of Pages: xviii+482
Meeting Date: 04/05/2002 – 04/07/2002
Location: Columbia, SC
Digital Object Identifier: 10.1109/.2002.995557
Posted online: 2002-08-07 00:51:13.0
Abstract
We discuss the application of the Zipf-Mandelbrot law on musical pieces encoded in MIDI. Our hypothesis is that this will allow us to computationally identify and emphasize aesthetic aspects of music. We have identified an initial set of attributes (metrics) of music pieces on which to apply the Zipf-Mandelbrot law. These metrics include pitch of musical events, duration of musical events, the combination of pitch and duration of musical events, and several others. An experimental study of 33 MIDI-encoded pieces supports this hypothesis

User-adaptive music emotion recognition

Wang Muyuan Zhang Naiyao Zhu Hancheng
Dept. of Autom., Tsinghua Univ., Beijing, China

This paper appears in: Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Publication Date: 31 Aug.-4 Sept. 2004
Volume: 2
On page(s): 1352 – 1355 vol.2
Number of Pages: 3 vol. 1807
ISSN:
Digital Object Identifier: 10.1109/ICOSP.2004.1441576
Posted online: 2005-06-27 11:07:52.0
Abstract
Music can arouse profound and deep emotional reactions and the automatic emotion recognition of music is useful for music information retrieval, human-computer interaction and affective computing Picard R.W. (1997). However, the nature of music is very complex and users' emotion responses vary from individual to individual. In this paper, we present an adaptive scheme to recognize the emotional meaning of music, which is able to follow users' preference. The recognition process is consisted of four steps: first, a two-dimensional model, 'emotion plane' is used to model the emotion classes; second, novel musical perceptual features are extracted from MIDI files; then, different support vector machines (SVM) were trained according to different users' preferences and finally these trained support vector machines are used to classify the emotion of music. Satisfying experimental results are obtained on western tonal music, with different users. That indicates the effectiveness of our approach.

A method for solmization of melody

Yongwei Zhu Kankanhalli, M. Sheng Gao

This paper appears in: Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on
Publication Date: 27-30 June 2004
Volume: 3
On page(s): 1639 – 1642 Vol.3
Number of Pages: 3 vol (xxviii+2242)
ISSN:
Posted online: 2005-02-22 08:35:51.0
Abstract
This work presents a novel method for the automatic solmization of a melody, by which a melody (a sequence of MIDI notes) can be transcribed to sol-fa syllables (i.e., do, re, me, fa, sol, la, ti). Automatic solmization can assist in music skill training, music notation and content-based music retrieval. The proposed method is based on an approach for estimating the music scale of a melody. The key of the major scale (“do") is estimated using music scale models. Due to the diversity of melody types, models for both diatonic and pentatonic scales are employed to avoid the possible key ambiguity for folk songs. The decision of the key of a melody is based on the scale estimation results for aggregating music notes, so that the method can work for both short and long melodies. Experiments have shown that the technique can achieve 95% correct solmization of the melodies of pop songs.

A music retrieval system based on the extraction of non trivial recurrent themes and neural classification

Colaiocco, B. Piazza, F.
Dip. Elettronica e Autom., Ancona Univ., Italy

This paper appears in: Neural Networks, 2003. Proceedings of the International Joint Conference on
Publication Date: 20-24 July 2003
Volume: 2
On page(s): 1110 – 1115 vol.2
Number of Pages: 4 vol. (lxiv+3261)
ISSN: 1098-7576
Digital Object Identifier: 10.1109/IJCNN.2003.1223846
Posted online: 2003-08-26 09:04:00.0
Abstract
In this paper we propose a new approach for music features extraction used for fast content-based retrieval of songs from a suitable built database. The algorithm discovers, by an interaction with the program manager, the refrain of type O MIDI songs and builds a database in which musical features and text information such as title, author, genre, etc. are stored. A neural network architecture is trained only by the features from the refrain of all the songs in the database belonging to an appropriate sub-class, and performs the retrieval in query-by-humming problem kind. Elman recurrent neural nets are used. Experimental results show the effectiveness of the proposed approach.

Musical style identification using self-organising maps

de Leon, P.J.P. Inesta, J.M.
Dept. Lenguajes y Sistemas Informaticos, Alicante Univ., Spain

This paper appears in: Web Delivering of Music, 2002. WEDELMUSIC 2002. Proceedings. Second International Conference on
Publication Date: 9-11 Dec. 2002
On page(s): 82 – 89
Number of Pages: x+231
ISSN:
Digital Object Identifier: 10.1109/WDM.2002.1176197
Posted online: 2003-02-06 11:15:55.0
Abstract
In this paper the capability of using self-organising neural maps (SOM) as music style classifiers from symbolic specifications of musical fragments is studied. From MIDI file sources, the monophonic melody track is extracted and cut into fragments of equal length. From these sequences, melodic, harmonic, and rhythmic numerical descriptors are computed and presented to the SOM. Their performance is analysed in terms of separability in different music classes from the activations of the map, obtaining different degrees of success for classical and jazz music. This scheme has a number of applications like indexing and selecting musical databases or the evaluation of style-specific automatic composition systems.

Music style mining and classification by melody

Man-Kwan Shan Fang-Fei Kuo Mao-Fu Chen
Dept. of Comput. Sci., Nat. Chengchi Univ., Taipei, Taiwan

This paper appears in: Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on
Publication Date: 26-29 Aug. 2002
Volume: 1
On page(s): 97 – 100 vol.1
Number of Pages: 2 vol. (xxx+924+625)
ISSN:
Digital Object Identifier: 10.1109/ICME.2002.1035727
Posted online: 2002-11-07 17:11:48.0
Abstract
Music style is one of the features that people used to classify music. Discovery of music style is helpful for the design of a content-based music retrieval system. In this paper we investigate the mining and classification of music style by melody from a collection of MIDI music. We extract the chord from the melody and investigate the representation of extracted features and corresponding mining techniques for music classification. Experimental results show that the classification accuracy is about 70% to 84% for 2-way classification.

Distance metrics and indexing strategies for a digital library of popular music

Francu, C. Nevill-Manning, C.G.
Dept. of Comput. Sci., Rutgers Univ., Piscataway, NJ, USA;

This paper appears in: Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on
Publication Date: 30 July-2 Aug. 2000
Volume: 2
On page(s): 889 – 892 vol.2
Number of Pages: 3 vol. xxxv+17778
Meeting Date: 07/30/2000 – 08/02/2000
Location: New York, NY
Digital Object Identifier: 10.1109/ICME.2000.871502
Posted online: 2002-08-06 23:14:10.0
Abstract
People identify powerfully with music: someone might say “that's my song!” but they are unlikely to say “that's my book!” or “that's my picture!” A digital library of popular music therefore has the potential to be a compelling application of information retrieval technology. Such a library requires a retrieval method that is appropriate for a non-technical audience. Experiments on “query by humming”, which attempt to retrieve a tune based on sampled recording of a user singing an excerpt, have heretofore concentrated on relatively small, well-curated collections. Scaling up introduces three problems: availability of source material, an increase in false positive hits, and slower retrieval. We describe our experiments with MIDI files, propose a new, more accurate distance metric between queries and songs, and discuss possibilities for efficient indexing

Music information retrieval system using complex-valued recurrent neural networks

Kataoka, M. Kinouchi, M. Hagiwara, M.
Fac. of Sci. & Technol., Keio Univ., Yokohama , Japan;

This paper appears in: Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Publication Date: 11-14 Oct. 1998
Volume: 5
On page(s): 4290 – 4295 vol.5
Number of Pages: 5 vol. 4945
Meeting Date: 10/11/1998 – 10/14/1998
Location: San Diego, CA
Digital Object Identifier: 10.1109/ICSMC.1998.727520
Posted online: 2002-08-06 22:16:32.0
Abstract
We propose a music information retrieval system using complex-valued recurrent neural networks. Melodies can be treated as temporal sequences. The multilayer network using complex neurons with local feedback (MNCF) is used in the proposed system because of the high ability to deal with temporal sequences. The process of retrieval is as follows: first, the pitch and duration of each note are extracted from the key melody which is inputted from the MIDI keyboard. Second, they are inputted to some MNCFs. When the output values of each MNCF agree with the next input values for several times, it produces the database address. The user can listen to the candidate of the melody. In addition, the user can know the text information. The proposed system has the following other features: the user can input any parts of the melody he/she remembers as a key input; the human interface is excellent for users. The retrieval is performed in parallel because of the inherent parallelism of neural networks; the proposed system is robust for transposition and change of the tempo. We have evaluated the proposed system by experiment. The system retrieved about 91.5% of melodies correctly

Busy Holiday

悠忙假期

2 則評論在 IEEE Research Papers.

發表迴響取消回覆

相關文章

2 則評論在 IEEE Research Papers.

發表迴響 取消回覆

發表迴響取消回覆