Continuous Pitch Contour as an Improvement Feature for Music Information Retrieval by Humming/Singing

Autor:	Quan Vu Hai, Tri Nguyen Truong Duc, Minh Nhat, Ha Nguyen Duc Hoang
Rok vydání:	2008
Předmět:	Dynamic time warping Sequence (music) ComputingMethodologies_PATTERNRECOGNITION Matching (graph theory) Computer science Feature (computer vision) Speech recognition Music information retrieval Singing Pitch contour Smoothing
Zdroj:	PRICAI 2008: Trends in Artificial Intelligence ISBN: 9783540891963 PRICAI
DOI:	10.1007/978-3-540-89197-0_111
Popis:	In this paper we present a method for smoothing the pitch sequence to remove the outliers caused by pitch tracking method and errors in sung/hummed voice. This approach is used for constructing a query by singing/humming system. After the pitch sequence is smoothed, the continuous pitch contour is calculated. Then, this feature can be used with Dynamic Time Warping (DTW) matching to compute the difference score between the each query and song. Experimental result of this method on TCS Corpus for query by Singing/Humming will be reported and discussed in detail in this paper.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::46811b35a7c319b58c99ccaeccaf7a4b https://doi.org/10.1007/978-3-540-89197-0_111 Zobrazit plný text záznamu