Several people have spent parts of their academic career on optical character recognition of tablature. Of course, given the error rates, a human musician might still be useful to proofread any automatic output.
I am not aware of a playback function, but once the sound information is digitalised, a MIDI output should be possible to program. (But then again, "since when is MIDI music?") Christoph Dalitz & Tim Crawford (2013): From Facsimile to content based retrieval: the electronic corpus of lute music. Phoibos - Zeitschrift für Zupfmusik 2/2013:167-185. http://lionel.kr.hsnr.de/~dalitz/data/publications/phoibos-ecolm.pdf Christoph Dalitz & Christine Pranzas (2009): German Lute Tablature Recognition. Conference Paper, read at the 10th International Conference on Document Analysis and Recognition, ICDAR 2009, Barcelona, Spain, 26-29 July 2009. doi:10.1109/ICDAR.2009.52 https://www.researchgate.net/publication/220860518_German_Lute_Tablature_Recognition Possibly also relevant in this context: de Valk, R. (2015). Structuring lute tablature and MIDI data: Machine learning models for voice separation in symbolic music representations. (Doctoral thesis, City, University of London) http://openaccess.city.ac.uk/15659/ 2017-02-04 19:46 GMT+01:00 Leonard Williams <arc...@verizon.net>: > Has anyone managed to devise an optical character reader which can > read > tablature and, given tuning parameters, play it back? Just curious; I'd > really rather hear (and watch) a human musician. > > Regards, > Leonard > > > > > To get on or off this list see list information at > http://www.cs.dartmouth.edu/~wbc/lute-admin/index.html
