An enormous global pet peeve since Digital Music collapsed from long unsegmented strings of PCM into inodes on a filesystem is Armed Forces in Alphabetical Order. The first ID3 spec, meant to associate the audio-only information in the MPEG stream with some “real world” characteristics, was pitiful: audio gets 1MB per minute but the concordant […]

Recent talks at Harvard (via Paris Smaragdis et al’s Statistical Techniques for Audio and Video Processing and also at MERL on usual text+music stuff. If you want the Harvard slides let me know, MERL’s was similar but more submarined “business stuff.” Take home message: Aimee Mann through the MFCC ringer equals success (thanks Dan.) Who […]

Kelly, Dan and I just had our paper at the IEEE biennial Workshop on Applications of Signal Processing to Audio and Acoustics, Learning Auditory Models of Machine Voices. We got the much vaunted “crackpot slot” (last paper on the last day,) an honor I haven’t had since… that time I presented text mining at ICMC […]

I saw my first Christmas decoration for sale at the local drug mart and was reminded to mention that yes, there will be a Singular Christmas update this year. Eigenradio’s phase-locked tentacles are not going anywhere for long! Look for the xmas card –
Relatedly, heavy work continues at the Nest. We’re on our 2nd espresso […]

I’ve gotten some queries about “The Echo Nest.” It’s Tristan Jehan and myself, we are in (quote) “secret” mode and we have a gorgeous office in Davis Sq., Somerville MA. Although we’ve had the “launch party” we’re holding off on publicly announcing anything for a short while. Check back here for more info on this […]

As MIT shuts down my page there I had to move over to this new site, which is probably better in the long run. Welcome to variogr.am. In this space I’ll be posting short updates on projects. If you’d like to write, do so at brian.whitman at variogr.am!