【導(dǎo)讀】-Virtualhomeof. -TheInternational. Audentify!Developers:F.Kurth,A.Ribbrock,M.Clausen. SystemDescription. Takessignalqueries(1-5seconds,96-128. Developers:F.Furth,M.Muller,D.Damm,C.Fremerey,Kurth,F.,Müller,M.,Damm,D.,Fremerey,Ch.Ribbrock,Kurth,F.,Müller,M.,Ribbrock,A.,Röder,T.,Damm,D.,Retrieval(ISMIR2020),Barcelona,Spain.URL:. SystemDescription. Querytype(s):audiofiles(mp3,wav,MIDI),lyrics,Generates“deriveddata”fromquery. extractsfeatures. Groot,S.,VanDenBerg,A.,TheSinging. URL:. SystemDescription:. Querybyhumming. U

　　

【正文】 Organization, Proceedings of the 25. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 02), pp. 409410, August 1115, 2020, in Tampere, Finland ? A. Rauber, and M. Fr252。hwirth, Automatically Analyzing and Organizing Music Archives, Proceedings of the 5. European Conference on Research and Advanced Technology for Digital Libraries (ECDL 2020), Sept. 48 2020, Darmstadt ? URL: SOMeJB (The SOM enhanced JukeBox) ? System Description: ?Interface is a static, webbased map where similar pieces of music are clustered together ?Music anized by a novel set of features based on rhythm patterns in a set of frequency bands and psychoacoustically motivated transformations ?Extracts features that apply to loudness sensation (intensity), and rhythm ?Selfanizing map algorithm is applied to anize the pieces on a map (trained neural work) SoundCompass ? Developers: Naoko Kosugi, Yuichi Nishihara, Tetsuo Sakata, Masashi Yamamuro and Kazuhiko Kushima, NTT Laboratories ? System Description: ? User sets a metronome and hums melody in time with clicks ? Database songs have three feature vectors ? Tone Transition Feature Vector: contains the dominant pitch for each 16beat window ? Partial Tone Transition Feature Vector: Covers a time window different from the Tone Transition Feature Vector ? Tone Distribution Feature Vector: histogram containing note distribution ? Query is matched against each of the vectors, results are bined by determining the minimum Tararira ? Developers: Ernesto L243。pez, Martin Rocamora, Gonzalo Sosa ? Relevant Publications: ?E. Lopez y M. Rocamora. Tararira: Sistema de bsqueda de msica por melod237。a cantada. X Brazilian Symposium on Computer Music. October, 2020. ? URL: os/gmm/proyectos/tararira/ Tararira ? System Description: ?User submits a hummed query ?Pitch tracking applied to query ?Audio segmentation determines note boundaries ?Melodic analysis adjusts pitches to tempered scale ?Results found by coding query note sequence, find occurrences using flexible similarity rules (string matching), and refining the selection using pitch time series TreeQ ? Developer: Jonathan Foote ? Publications: ?Foote, ., ContentBased Retrieval of Music and Audio, . J. Kuo et al., editor, Multimedia Storage and Archiving Systems II, Proc. of SPIE, Vol. 3229, pp. 138147, 1997 ? URL: TreeQ ? System Description: ? Primarily query by example, can also search by classification ? Tree based supervised vector quantizer is built from labeled training data ? Database audio is parameterized via conversion into MFCC and energy vectors ? Each resulting vector is quantized into the tree ? Vector space divided into “bins”, any MFCC vector will fall into one bin ? A histogram based on the distribution of MFCC vectors into each bin is created for query and database audio ? Songs matched based on histograms of feature counts at tree leaves ? Distance is determined using Euclidian distance between corresponding templates of each audio clip ? Results sorted by magnitude and returned as a ranked list VisiTunes ? Developers: Scott McCaulay ? Further Information: / ? URL: ? System Description: ? Uses audio content of songs to calculate similarity between music and creates playlists based on the results ? Converts sample values of each frame to frequency data ? Extracts sum total of sound energy by frequency band ? Uses results to simplify audio data into 256 integer values for fast parison