The whole premise of the comment you were replying to was that we were spinning our wheels, which is not an utter refusal of progress but a characterization of progress. You responded with marveling at the things which have been achieved which you find remarkable and unappreciated. I responded by characterizing those as having some qualities of remarkability and novelty which ultimately fail to exceed wheel spinning. You are now accusing me of having set up an unreasonable standard of progress. There are two characterizations of the progress in this domain which I believe are likely but not certain accounts, maybe both are partially true, maybe just one, but both are contained by the wheelspinning metaphor. One is that progress is being made, but the progress is not forward and in fact the progress is the digging of a deeper and deeper hole that makes actual progress more difficult, and the other is that progress is being made, but that progress is that of an infinite series which logarithmically ascends from 1.0 to 1.1. There were genuine discoveries, inspiration and novelty required on the road from note identification to chord identification and deconstruction that could be reversed and reconstructed with reasonable accuracy. That does not mean that we aren't doing anything more than refining and improving the accuracy of processes which we were already performing rudimentary forms of 20+ years ago. I'm not saying there isn't progress, only that the progress is limited, and we are now reaching towards the same limits which we had begun approaching at the inception of the programmable machine and there is no escape in sight.

https://www.jstor.org/stable/3679550?seq=1

"The real power of a neural net is its ability to compute solutions for distributed representations. In most cases, the solutions for these complex cases are not obvious. The pitch class representation of pitch is a local rather than a distributed one. In this case a possible solution for the chord classification problem is apparent without the use of a learning algorithm. A net containing 36 hidden units, one representing each of the possible major, minor, and diminished triads, could be constructed so as to map chords to chord types. Thus our interest in using a pitch class representation was not to find this obvious solution, but to find a solution which used a minimum number of hidden units. We hypothesized that three hidden units would be adequate and that the hidden units would form concepts of the intervals found in triads: i.e., major third, minor third, perfect fifth, and diminished fifth.

Each pitch-class net used 12 input units to represent the 12 pitches of the chromatic scale and 3 Output units to represent chord type. The number of hidden units and the values of the learning parameters are summarized in Table 1 for each of the eight pitch class nets discussed. Net 1 had an adjacent layer architecture as shown in Fig. 2 and three hidden units. It identified 25 percent of the chords after more than 11,000 learning epochs. When a fully connected architecture was used in conjunction with three hidden units in Net2, 72 percent of the chords were identified after 2,800 learning epochs. "

https://secure.aes.org/forum/pubs/conventions/?elib=11400