Musical genre classification of MPEG-4 TwinVQ audio data

Autor:	Mamoru Hoshi, Michihiro Kobayakawa
Rok vydání:	2011
Předmět:	Audio signal Computer science Speech recognition Feature extraction TwinVQ Data_CODINGANDINFORMATIONTHEORY computer.file_format Linear predictive coding Cepstrum MPEG-4 Dynamic range compression Bitstream computer Transform coding
Zdroj:	ICME
DOI:	10.1109/icme.2011.6012195
Popis:	We proposed a musical feature based on LSP (Line Spectrum Pair) parameter directly extracted from the bitstream in the MPEG-4 TwinVQ audio data. Our key idea is to extract the musical features by using information stored in the bitstream without decoding to audio signals. In this paper, we propose two musical features for musical genre classification of MPEG-4 TwinVQ audio data.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::99964c535d03e433f782874ad38da3b8 https://doi.org/10.1109/icme.2011.6012195 Zobrazit plný text záznamu