Fw: [Sigia-l] "Search Inside the Music"

[Geoff Froh]

----- Original Message ----- 
From: "Geoff Froh" <geoff.froh at densho.org>
To: "Ziya Oz" <listera at earthlink.net>
Sent: Wednesday, July 12, 2006 9:28 AM
Subject: Re: [Sigia-l] "Search Inside the Music"


> There was a company called CantaMetrics back around 2000 that was 
> experimenting with this type of audio analysis mainly for IP protection 
> purposes. They were also investigating the use of their technology for 
> some of the things Sun is talking about. I seem to recall rumors that 
> Singing Fish was engaged with them somehow.
>
> Another interesting automated genre identification approach is network 
> analysis of user-tagged resources. There was a paper late last year by 
> Lamblotte and Ausloos, "Collaborative tagging as a tripartite network" 
> (http://arxiv.org/abs/cs.DS/0512090), where the authors applied a number 
> of inferencing models and visualizations against public tagging 
> environments. They were able to do some potentially interesting things 
> with their last.fm dataset including identifying tag/user/resource 
> patterns that might suggest genre.
>
> That being said, I'm also dubious about the efficacy of "automated" 
> methods. The idea of genre classification goes back a long time -- see 
> Alan Lomax's work on "cantometrics" for example -- but it becomes 
> extremely difficult with music that either consciously or unconsciously 
> draws from multiple genres. It seems like looking *exclusively* at the 
> structure of the music itself might not produce good results. Maybe 
> combining audio analysis with sources of user-driven evidence (i.e., 
> tagging) could provide something more interesting.
>
> geoff froh
>
>
> ----- Original Message ----- 
> From: "Ziya Oz" <listera at earthlink.net>
> To: "SIGIA-L" <sigia-l at asis.org>
> Sent: Tuesday, July 11, 2006 11:32 PM
> Subject: [Sigia-l] "Search Inside the Music"
>
>
>>A research project at Sun Labs is exploring new methods of searching music
>> by its acoustic content and context. This project is aimed at helping 
>> people
>> find and organize their music based on the properties of the music 
>> itself:
>> lyrics, musical theme, melody, tempo, rhythm, and instrumentation.
>> [...]
>> For example, said Mr. Lamere, the technology could be used for audio
>> indexing (i.e., to find the Maynard Ferguson trumpet solo in a long jazz
>> piece). It could be used for thumbnailing (for example, extracting the
>> chorus). It could be used for ³fingerprinting² a song for copyright
>> enforcement purposes. Movie producers could use it to quickly find mood
>> music that works with a particular scene. Eventually, we could even get 
>> to
>> the point where a person could hum a few bars and the system could 
>> identify
>> the song and locate a commercial version.
>>
>> Mr. Lamere also points out that music search capabilities could
>> fundamentally change the music experience itself. ³Think of what artists
>> could build and create if they had quick, easy access to specific sounds 
>> and
>> tones and rhythms from millions of songs,² he said. ³Think of the new 
>> music
>> communities that could arise and the new social interactions. I can 
>> picture
>> classical music buffs listening to three different conductors¹
>> interpretations of the Jupiter Symphony and then debating which is best.²
>>
>> According to Mr. Lamere, music search capabilities could also alter the
>> traditional ³hit-driven² business model of the music industry and lead to
>> broader exposure for everyone from garage bands to musicians in far-flung
>> corners of the globe. ³The Internet and the Web have already been huge in
>> leveling the playing field for musicians,² he said. ³Search Inside the 
>> Music
>> could be the last piece of the puzzle in helping listeners find new 
>> artists¹
>> music. You start getting recommendations based on the actual content of 
>> the
>> music, not popularity bias.²
>>
>> <http://research.sun.com/spotlight/2006/2006-06-28_search_inside_music.html>
>>
>> Farfetched?
>>
>> ----
>> Ziya
>>
>> Usability >  Simplify the Solution
>> Design >  Simplify the Problem
>>
>>
>>
>>
>> ------------
>> When replying, please *trim your post* as much as possible.
>> *Plain text, please; NO Attachments
>>
>> Searchable Archive at http://www.info-arch.org/lists/sigia-l/
>>
>> Most presentations/papers and posters have been loaded to the IA Summit 
>> 06 website:
>>
>> http://iasummit.org/2006/conferencedescrip.htm
>> http://iasummit.org/2006/posters.htm
>>
>>
>>
>> ________________________________________
>> Sigia-l mailing list -- post to: Sigia-l at asis.org
>> Changes to subscription: http://mail.asis.org/mailman/listinfo/sigia-l
>>
>