<div dir="ltr">Hi,<div><br></div><div>Polyphonic transcription of a single instrument is a hard and unsolved problem! </div><div><br></div><div>Although this thesis indicates excellent performances for guitar (98% recall / 93% precision), they did it in "lab" conditions. The author honestly admits : </div><div><br></div><div>"<i>These results are also biased by the fact
that they were generated using the same guitar that generated the note templates,
and most notes were played at a constant volume. Playing very quietly or loudly would result in less accurate note detection. This test reflects the best performance of our implementation of the NMF
algorithm. [...] Unfortunately, the algorithm performed very poorly on a distorted electric
guitar input.</i>"</div><div><br></div><div>Other recent papers [1] focusing on piano transcription and using larger evaluation datasets announce around 90% precision/recall. Although my bibliography is not exhaustive, deep learning approaches [2] do not seem perform better than "classical" machine learning :/</div><div><br></div><div>The bad news is that those researchers don't want to share their code... or sometime lost their code, so one has to implement by her/himself based on the papers.</div><div><br></div><div>Cheers</div><div><br></div><div>Martin</div><div><br></div><div>[1] <a href="http://www.cp.jku.at/research/papers/Boeck_Schedl_ICASSP_2012.pdf">http://www.cp.jku.at/research/papers/Boeck_Schedl_ICASSP_2012.pdf</a><br></div><div>[2] <a href="http://cs.stanford.edu/~jngiam/papers/ismir2011-PolyphonicTranscription.pdf">http://cs.stanford.edu/~jngiam/papers/ismir2011-PolyphonicTranscription.pdf</a></div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">2015-10-19 23:15 GMT+02:00 <span dir="ltr"><<a href="mailto:emersont1@outlook.com" target="_blank">emersont1@outlook.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><p dir="ltr"><br>
Hello<br>
For polyphonics, I think that this paper, if it has not already been put forth, may help (I reuploaded the paper to puush to shorten the URL <a href="http://puu.sh/kQiCv/c43c603455.pdf" target="_blank">http://puu.sh/kQiCv/c43c603455.pdf</a>).<br>
I haven't quite had time to read it all, but I think that it would help with making aubio polyphonic<br>
Sent by <a href="http://taps.io/outlookmobile" target="_blank">Outlook</a> for Android<br>
</p>
<br>_______________________________________________<br>
aubio-user mailing list<br>
<a href="mailto:aubio-user@aubio.org">aubio-user@aubio.org</a><br>
<a href="https://lists.aubio.org/listinfo/aubio-user" rel="noreferrer" target="_blank">https://lists.aubio.org/listinfo/aubio-user</a><br></blockquote></div><br></div>