%0 Journal Article %1 Knees2007 %A Knees, Peter %A Pohle, Tim %A Schedl, Markus %A Widmer, Gerhard %D 2007 %K Algorithms Computing General H33 H55 In-terfaces Information Keywords: Music Presentation-Sound Re-trieval,context-based Retrieval; Storage Systems]: Terms: [Information and engine,Music mir musicsearch retrieval,cross-media retrieval,music search similarity uncovr %T A Music Search Engine Built upon Audio-based and Web-based Similarity Measures %U http://www.findsounds.com %X An approach is presented to automatically build a search engine for large-scale music collections that can be queried through natural language. While existing approaches depend on explicit manual annotations and meta-data assigned to the individual audio pieces, we automatically derive descriptions by making use of methods from Web Retrieval and Music Information Retrieval. Based on the ID3 tags of a collection of mp3 files, we retrieve relevant Web pages via Google queries and use the contents of these pages to characterize the music pieces and represent them by term vectors. By incorporating complementary information about acoustic similarity we are able to both reduce the dimensionality of the vector space and improve the performance of retrieval, i.e. the quality of the results. Furthermore, the usage of audio similarity allows us to also characterize audio pieces when there is no associated information found on the Web. %@ 9781595935977

@article{Knees2007, abstract = {An approach is presented to automatically build a search engine for large-scale music collections that can be queried through natural language. While existing approaches depend on explicit manual annotations and meta-data assigned to the individual audio pieces, we automatically derive descriptions by making use of methods from Web Retrieval and Music Information Retrieval. Based on the ID3 tags of a collection of mp3 files, we retrieve relevant Web pages via Google queries and use the contents of these pages to characterize the music pieces and represent them by term vectors. By incorporating complementary information about acoustic similarity we are able to both reduce the dimensionality of the vector space and improve the performance of retrieval, i.e. the quality of the results. Furthermore, the usage of audio similarity allows us to also characterize audio pieces when there is no associated information found on the Web.}, added-at = {2021-10-15T08:46:33.000+0200}, author = {Knees, Peter and Pohle, Tim and Schedl, Markus and Widmer, Gerhard}, biburl = {https://www.bibsonomy.org/bibtex/295bfaddd91750df43aa13ce5c6620283/simonha94}, interhash = {9383b4634be83fe6b6f4a0d6a6fbf0da}, intrahash = {95bfaddd91750df43aa13ce5c6620283}, isbn = {9781595935977}, keywords = {Algorithms Computing General H33 H55 In-terfaces Information Keywords: Music Presentation-Sound Re-trieval,context-based Retrieval; Storage Systems]: Terms: [Information and engine,Music mir musicsearch retrieval,cross-media retrieval,music search similarity uncovr}, timestamp = {2021-10-15T08:52:55.000+0200}, title = {A Music Search Engine Built upon Audio-based and Web-based Similarity Measures}, url = {http://www.findsounds.com}, year = 2007 }