# A Bi-directional Transformer for Musical Chord Recognition Source: [A Bi-directional Transformer for Musical Chord Recognition]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:41:29.853Z Authors: Jonggwon Park, Kyoyun Choi, Sungwook Jeon, Dokyun Kim, Jonghun Park Published: 2019-07-05T07:00:38.000Z ## Abstract Chord recognition is an important task since chords are highly abstract and descriptive features of music. For effective chord recognition, it is essential to utilize relevant context in audio sequence. While various machine learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been employed for the task, most of them have limitations in capturing long-term dependency or require training of an additional model. In this work, we utilize a self-attention mechanism for chord recognition to focus on certain regions of chords. Training of the proposed bi-directional Transformer for chord recognition (BTC) consists of a single phase while showing competitive performance. Through an attention map analysis, we have visualized how attention was performed. It turns out that the model was able to divide segments of chords by utilizing adaptive receptive field of the attention mechanism. Furthermore, it was observed that the model was able to effectively capture long-term dependencies, making use of essential information regardless of distance. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Chord Recognition on uspop2002 170-label large vocabulary (val)](): Chord Recognition; uspop2002 170-label large vocabulary (val); Root: 80.51. - [Chord Recognition on uspop2002 25-label maj-min vocabulary (val)](): Chord Recognition; uspop2002 25-label maj-min vocabulary (val); Root Accuracy: 82.02. - [Automatic Chord Estimation on ACR (test)](): Automatic Chord Estimation; ACR (test); Root Accuracy: 81.52. - [Chord Recognition on BTC (test)](): Chord Recognition; BTC (test); Root Accuracy: 83.5. - [Chord Segmentation on BTC (test)](): Chord Segmentation; BTC (test); Underestimation Rate: 90.1. ## Original sources and implementation [Original paper]() [PDF]()