Abstract
Automatic chord recognition (ACR) has long been a topic of interest in the field of Music Information Retrieval (MIR), due to not only its commercial applications, but also its support for advanced music analysis. While a lot of ACR-related work deals with audio data, ACR from symbolic music has received less attention. In addition, conventional ACR systems specify chords in a key-dependent way (usually with the root note and the chord quality) and hence are unable to reveal the high-level patterns and harmonic structures. These issues hinder the developments of music analysis and music generation via ACR systems. With the success of deep learning, it is viable to build a symbolic ACR system using a more comprehensive chord vocabulary such as functional harmony. Recently, two advanced models, namely the Bi-directional Transformer for Chord Recognition (BTC) and the Harmony Transformer (HT), introduced for the first time the multi-head attention mechanism to ACR, showing the great capability of the attention mechanism to improve the performance of ACR. In this paper, we systematically study the performance of the BTC and the HT in terms of symbolic ACR, and propose an improved model. Experiments on conventional ACR and advanced functional harmony recognition indicate that the HT has the potential to surpass the BTC, especially in terms of chord segmentation quality. Also the overall performance of the HT is further improved by enhancing the learning of local context and positional information.
Highlights
1.1 Automatic Chord Recognition Chord recognition is a process to identify the harmonic entity of each musical segment, usually by giving a chord name to the segment in question
With evaluations on the conventional chord recognition and the functional harmony recognition tasks, we show that the Harmony Transformer (HT) is more promising than the Bi-directional Transformer for Chord Recognition (BTC) in terms of recognition accuracy and segmentation quality; it is validated that the proposed improvements advance the overall performance of Automatic chord recognition (ACR)
For the BTC-FC, the substitution of the fully-connected feedforward network (FFN) for the convolutional one is harmful to the performance in most of the cases, because a fully-connected network only computes the weighted sum of its inputs and does not take into account the temporally adjacent information which helps relate local features to higher-level semantics (Ren et al, 2019)
Summary
1.1 Automatic Chord Recognition Chord recognition is a process to identify the harmonic entity of each musical segment, usually by giving a chord name to the segment in question. This problem is not as simple as it may seem, for it concerns several aspects of musical harmony, and the answer to the problem may not be unique. The chord vocabulary differs according to musical style and context. The boundary of each segment which deserves to be recognized as a single chord is not explicitly defined by the music itself. It is usually difficult to partition music into harmonically meaningful segments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
