Here, content-based means that, in the comparison of music data, the system makes use of the raw music data itself (e.g., from the music recording or the YouTube video), rather than relying on manually generated keywords referring to the artists’ names, the song’s title or lyrics ( Müller, 2007). Assuming that the student has already a partial or even a complete transcription of the solo available, content-based retrieval techniques could help to resolve this problem. In the case that the student searches for a musician whose name is not mentioned in the metadata (e.g., because the musician was “only” a sideman in the band), a textual search may not be successful or may result in too many irrelevant results. Imagine a jazz student who is practicing a jazz solo played by a famous musician and is now interested in the original recording. The lack of reliable metadata makes it hard to identify particular recordings, especially for music genres where many renditions of the same musical work exist (e.g., symphonies in Western classical music, ragas in Indian music, or standards in jazz music). However, since this metadata is not curated, it might be incomplete or incorrect. Often, these performances are tagged with basic metadata-mainly the artist and the title of the song. Many of these videos contain recordings of music performances. Online video platforms, such as YouTube, make billions of videos available to users from all over the world. Our contribution illustrates the potential of modern web-based technologies for the digital humanities, and novel ways for improving access and interaction with digitized multimedia content. Furthermore, we integrate publicly available data resources from the Semantic Web in order to extend the presented information, for example, with a detailed discography or artists-related information. We then embed the retrieved videos in a recently developed web-based platform and enrich the videos with solo transcriptions that are part of the WJD.
![sonic visualiser youtube sonic visualiser youtube](https://i.ytimg.com/vi/IXvlVPLCStc/maxresdefault.jpg)
With these techniques, we were able to identify 988 corresponding YouTube videos for 329 solos out of 456 solos contained in the WJD.
![sonic visualiser youtube sonic visualiser youtube](https://i.ytimg.com/vi/1HC4GEizPBw/maxresdefault.jpg)
First, we establish a link between the WJD annotations and corresponding YouTube videos employing existing retrieval techniques. The WJD contains various annotations related to famous jazz solos. In this paper, we consider a research corpus called the Weimar Jazz Database (WJD) as an illustrating example scenario. Our web-based tools offer researchers and music lovers novel possibilities to interact with and navigate through the content.
![sonic visualiser youtube sonic visualiser youtube](https://i.ytimg.com/vi/xdt1ADvNwLE/maxresdefault.jpg)
With our contribution, we want to bridge this gap by enriching publicly available multimedia content with musical annotations available in research corpora, while maintaining easy access to the underlying data. Although they have great potential, these musical annotations are often inaccessible to users outside the academic world.
![sonic visualiser youtube sonic visualiser youtube](https://i.ytimg.com/vi/nepm_IOR02M/maxresdefault.jpg)
On the other hand, a vast amount of high-quality and musically relevant metadata has been annotated in research areas such as Music Information Retrieval (MIR). Especially in the case of web services with user-supplied content, e.g., YouTube™, the available metadata is often incomplete or erroneous. Web services allow permanent access to music from all over the world.