用于高效捕捉音乐信号声学特性的改进型高分辨率钢琴转录架构
Improved Architecture for High-resolution Piano Transcription to Efficiently Capture Acoustic Characteristics of Music Signals
AI总结：
本文针对高分辨率钢琴转录中泛音误检和模型过大的问题，提出基于常数Q变换与CRNN及非自回归Transformer解码器结合的改进架构，在提升音符级指标的同时显著减小模型规模。
摘要：
自动音乐转录（AMT）旨在将音乐信号转换为乐谱，是音乐信息检索中的重要任务之一。近年来，已有研究将高分辨率标签（即钢琴音符的连续起音和止音时间）作为训练目标，显著提升了转录性能。然而，仍有一些问题有待解决，例如音符的泛音有时会被识别为假阳性音符，并且为了提高转录性能，AMT模型的规模往往趋于增大。为解决这些问题，我们提出了一种改进的高分辨率钢琴转录模型，以更好地捕捉音乐信号的特定声学特性。首先，我们采用常数Q变换作为输入表示，以更好地适应音乐信号。此外，我们设计了两种架构：第一种基于带有空洞卷积的卷积循环神经网络（CRNN），第二种是编码器-解码器架构，将CRNN与非自回归Transformer解码器相结合。我们对所提出的模型进行了系统性实验。与作为基线的高分辨率AMT系统相比，我们的模型有效地实现了：1）音符级指标的持续提升；2）显著更小的模型规模，这为未来工作提供了启示。
英文摘要：
Automatic music transcription (AMT), aiming to convert musical signals into musical notation, is one of the important tasks in music information retrieval. Recently, previous works have applied high-resolution labels, i.e., the continuous onset and offset times of piano notes, as training targets, achieving substantial improvements in transcription performance. However, there still remain some issues to be addressed, e.g., the harmonics of notes are sometimes recognized as false positive notes, and the size of AMT model tends to be larger to improve the transcription performance. To address these issues, we propose an improved high-resolution piano transcription model to well capture specific acoustic characteristics of music signals. First, we employ the Constant-Q Transform as the input representation to better adapt to musical signals. Moreover, we have designed two architectures: the first is based on a convolutional recurrent neural network (CRNN) with dilated convolution, and the second is an encoder-decoder architecture that combines CRNN with a non-autoregressive Transformer decoder. We conduct systematic experiments for our models. Compared to the high-resolution AMT system used as a baseline, our models effectively achieve 1) consistent improvement in note-level metrics, and 2) the significant smaller model size, which shed lights on future work.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
