hey, You can find links to talks he's given - such a kind gesture given the lack of free resources and machine learning applied to audio compared to other topics. From a lecture recording, it appears the algorithm comprises of deep neural network with a mask approach. This has been used to improve hearing aids too for example and as far as I know, believing in izotope's blog post, this is how izotope RX does the de-rustle for microphone noise.
I'd love to hear if others have been using DNN for audio, I am a bit more interested in DNN processing audio (ie, outputs processed audio) than classic classification approaches where people are mostly borrowing ideas from computer vision and classifying based on spectrogram representations (think SFFT). Cheers b On Fri, Sep 6, 2019 at 9:10 AM Andrew Luke Nesbit <em...@andrewnesbit.org> wrote: > Yes, indeed. I would also love to learn more about this. I worked on > audio source separation for my PhD and postdoctoral research some years > ago. > > The webpage says to write to Roger directly ("For more info, please > contact Roger Jang.") > > Andrew > > On 06/09/2019 13:42, Patric Schmitz wrote: > > Impressive! Is the algorithm published and/or is it implemented in your > > Speech & Audio Processing Toolbox? > > > > Thank you, > > Patric > > > > On 9/6/19 8:21 AM, Jyh-Shing Roger Jang wrote: > >> Dear community: > >> (Sorry for cross posting, if any.) > >> I???d like to bring your attention to our recent demo system for > >> singing voice separation: > >> http://mirlab.org/demo/svs > >> You can simply input a youtube link and the system can separate the > >> vocal from background music. Feel free to let me know if you have any > >> questions. > >> J.-S. Roger Jang (?????????) > >> Prof, CSIE Dept, National Taiwan Univ, Taiwan (http://mirlab.org/jang) > >> > >> _______________________________________________ > >> dupswapdrop: music-dsp mailing list > >> email@example.com > >> https://lists.columbia.edu/mailman/listinfo/music-dsp > >> > > _______________________________________________ > > dupswapdrop: music-dsp mailing list > > firstname.lastname@example.org > > https://lists.columbia.edu/mailman/listinfo/music-dsp > > > > -- > OpenPGP key: EB28 0338 28B7 19DA DAB0 B193 D21D 996E 883B E5B9 > _______________________________________________ > dupswapdrop: music-dsp mailing list > email@example.com > https://lists.columbia.edu/mailman/listinfo/music-dsp > >
_______________________________________________ dupswapdrop: music-dsp mailing list firstname.lastname@example.org https://lists.columbia.edu/mailman/listinfo/music-dsp