Re: [music-dsp] [admin] Re: note onset detection
On Wed, 7 Aug 2013, Eric Battenberg wrote: What sort of email programs are people using that can't handle html? Pine? emacs/rmail-mode /bin/mail -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
Re: [music-dsp] [admin] Re: note onset detection
I can see the above binary, which implies that attaching a pretty explanatory image can be done without resorting to HTML (just not in line). So I'll say no HTML too. (I use gmail myself, but I use it on a text-based browser. I also occasionally use mailx to access gmail.) What sort of email programs are people using that can't handle html? Useful ones. Too useful for anyone to be grumbling about ticking one checkbox. -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
[music-dsp] [admin] Re: note onset detection
And FWIW, maybe it's time to change that. Spam filters have gotten a lot better in the last few years. This is an OLD list, and back in the day attachments/HTML caused lots of problems. What do you all think? Should we allow HTML/attachments? best, douglas On 8/7/13 3:34 PM, douglas repetto wrote: Eric, it looks like you're sending HTML mail. The list only takes plain text. best, douglas On 8/7/13 3:01 PM, Eric Battenberg wrote: For the life of me, I can't get the list to stop ignoring my replies (I'm not even getting bounces), so just to be sure, I've CC'd everyone on the thread. I'd also recommend the Bello tutorial paper. It's a great overview. Here are some other papers that are worth looking at. One of the more recent approaches that seems to be winning evals uses a long short-term memory (LSTM) recurrent neural net [2,3]. This may be along the lines of what Ross Bencina was talking about: humans do it with reference to their knowledge of previously heard melodic fragments. I've found the multi-band Klapuri approach [6] to be quite effective for detecting notes with strong attack transients. For notes with less pronounced attacks, the method covered in [5] is designed to detect changes in pitch. The method in [5] is also discussed in the tutorial paper [4] (Spectral features using phase), so definitely read that paper. Best, Eric [1] S. Böck, F. Krebs, and M. Schedl, “Evaluating the online capabilities of onset detection methods,” presented at the International Society for Music Information Retrieval Conference, 2012. [2] S. Böck, A. Arzt, F. Krebs, and M. Schedl, “Online realtime onset detection with recurrent neural networks,” presented at the International Conference on Digital Audio Effects (DAFx-12), 2012. [3] F. Eyben, S. Böck, B. Schuller, and A. Graves, “Universal onset detection with bidirectional long-short term memory neural networks,” /Proc. of ISMIR/, 2010. [4] J. Bello, L. Daudet, S. A. Abdallah, C. Duxbury, M. Davies, and M. Sandler, “A tutorial on onset detection in music signals,” /IEEE Transactions on Speech and Audio Processing/, vol. 13, no. 5, p. 1035, 2005. [5] J. Bello, C. Duxbury, M. Davies, and M. Sandler, “On the use of phase and energy for musical onset detection in the complex domain,” /IEEE Signal Processing Letters/, vol. 11, no. 6, pp. 553–556, 2004. [6] A. Klapuri, “Sound onset detection by applying psychoacoustic knowledge,” /ICASSP/, 1999. On Wed, Aug 7, 2013 at 6:56 AM, Ross Bencina rossb-li...@audiomulch.com mailto:rossb-li...@audiomulch.com wrote: On 7/08/2013 12:23 PM, charles morrow wrote: Please explain your reference Roberts transcription notes for me. Robert expressed the following requirement: On 6/08/2013 6:01 AM, robert bristow-johnson wrote: the big problem i am dealing with is people singing or humming and changing notes. i really want to encode those pitch changes as new notes rather than as a continuation of the previous note (perhaps adjusted with MIDI pitch bend messages). My thought was that this kind of top down parsing requires some kind of musical knowledge that is not intrinsic to the signal. I.e. I don't think any kind of signal novelty function is going to tell you how to segment features at the note level of abstraction. I rather suspect that humans do it with reference to their knowledge of previously heard melodic fragments. Ross. -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/__music-dsp http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/__mailman/listinfo/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp -- ... http://artbots.org .douglas.irving http://dorkbot.org .. http://music.columbia.edu/cmc/music-dsp ...repetto. http://music.columbia.edu/organism ... http://music.columbia.edu/~douglas -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
Re: [music-dsp] [admin] Re: note onset detection
On 8/7/13 12:35 PM, douglas repetto wrote: And FWIW, maybe it's time to change that. Spam filters have gotten a lot better in the last few years. This is an OLD list, and back in the day attachments/HTML caused lots of problems. What do you all think? Should we allow HTML/attachments? would this mean we could attach little graphics and they would just display (assuming your email client isn't brain-dead)? sometimes attaching the plot of a math function or a LaTeX-like graphic of a math equation (instead of the ASCII math i have used since 1994) would be useful. -- r b-j r...@audioimagination.com Imagination is more important than knowledge. -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
Re: [music-dsp] [admin] Re: note onset detection
Please no HTML mail. It displays as goobledy gook, and my fiters ignore as it is usually spam. Attachments maybe -- easier to ignore On 8/7/13 12:35 PM, douglas repetto wrote: And FWIW, maybe it's time to change that. Spam filters have gotten a lot better in the last few years. This is an OLD list, and back in the day attachments/HTML caused lots of problems. What do you all think? Should we allow HTML/attachments? would this mean we could attach little graphics and they would just display (assuming your email client isn't brain-dead)? sometimes attaching the plot of a math function or a LaTeX-like graphic of a math equation (instead of the ASCII math i have used since 1994) would be useful. -- r b-j r...@audioimagination.com Imagination is more important than knowledge. -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
Re: [music-dsp] [admin] Re: note onset detection
Okay, I'm hoping this one finally makes it through. Despite the fact that I removed formatting in gmail, the message was still sent with an html header. I looked at the raw email message and it looks like gmail includes a plain text version in addition to the html version of the email. Is there any reason this isn't acceptable? Shouldn't email programs be able to just use the plaintext version if it wants to? Otherwise, why would gmail send both? The change I made this time was clicking the little down arrow in the lower corner of the gmail compose pane and selecting Plain text mode. I'm really hoping this finally solves it. I checked a raw email to myself and it looks like only a plain text version is included. What sort of email programs are people using that can't handle html? Pine? -Eric On Wed, Aug 7, 2013 at 1:54 PM, j...@cs.bath.ac.uk wrote: Please no HTML mail. It displays as goobledy gook, and my fiters ignore as it is usually spam. Attachments maybe -- easier to ignore On 8/7/13 12:35 PM, douglas repetto wrote: And FWIW, maybe it's time to change that. Spam filters have gotten a lot better in the last few years. This is an OLD list, and back in the day attachments/HTML caused lots of problems. What do you all think? Should we allow HTML/attachments? would this mean we could attach little graphics and they would just display (assuming your email client isn't brain-dead)? sometimes attaching the plot of a math function or a LaTeX-like graphic of a math equation (instead of the ASCII math i have used since 1994) would be useful. -- r b-j r...@audioimagination.com Imagination is more important than knowledge. -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp
Re: [music-dsp] [admin] Re: note onset detection
On Wed, 7 Aug 2013, Eric Battenberg wrote: What sort of email programs are people using that can't handle html? Pine? Which is /exactly/ why I use it. do you strip binary enclosures?: begin 644 nlnn.gif M1TE.#=A,@``(```/___RP`,@XR/JOM#Z.M-J+L]Z\ MPI$X3)N0-F@BHJQB?L^X0F7\WF@M^W0!K[Z`7Z(2^%!U_`94NUTN2H%G ME(FDQK!,JQ;;4[#LRT7+-9TUTS^QK`G-$8UDX\J$]_9GS-#W4?-7:'B( -F*BXR-CH^`A940``.P`` ` end -- dupswapdrop -- the music-dsp mailing list and website: subscription info, FAQ, source code archive, list archive, book reviews, dsp links http://music.columbia.edu/cmc/music-dsp http://music.columbia.edu/mailman/listinfo/music-dsp