Professional vocalists modulate their voice timbre or pitch to make their
vocal performance more expressive. Such fluctuations are called singing
techniques. Automatic detection of singing techniques from audio tracks can be
beneficial to understand how each singer expresses the performance, yet it can
also be difficult due to the wide variety of the singing techniques. A deep
neural network (DNN) model can handle such variety; however, there might be a
possibility that considering the characteristics of the data improves the
performance of singing technique detection. In this paper, we propose PrimaDNN,
a CRNN model with a characteristics-oriented improvement. The features of the
model are: 1) input feature representation based on auxiliary pitch information
and multi-resolution mel spectrograms, 2) Convolution module based on the
Squeeze-and-excitation (SENet) and the Instance normalization. In the results
of J-POP singing technique detection, PrimaDNN achieved the best results of
44.9% at the overall macro-F measure, compared to conventional works. We also
found that the contribution of each component varies depending on the type of
singing technique.

本文提出了一种基于深度神经网络且考虑数据特征的 CRNN 模型 PrimaDNN，使用音高信息和多分辨率 Mel 频谱作为输入特征，采用 Squeeze-and-excitation (SENets) 与 Instance normalization 卷积模块，成功检测 J-POP 歌唱技巧，并获得了最佳的 44.9% 的宏平均 F 计量结果。

PrimaDNN：面向特征的 DNN 歌唱技巧检测定制

PrimaDNN': A Characteristics-aware DNN Customization for Singing  Technique Detection

Instrument recognition is a fundamental task in music information retrieval,
yet little has been done to predict the presence of instruments in
multi-instrument music for each time frame. This task is important for not only
automatic transcription but also many retrieval problems. In this paper, we use
the newly released MusicNet dataset to study this front, by building and
evaluating a convolutional neural network for making frame-level instrument
prediction. We consider it as a multi-label classification problem for each
frame and use frame-level annotations as the supervisory signal in training the
network. Moreover, we experiment with different ways to incorporate pitch
information to our model, with the premise that doing so informs the model the
notes that are active per frame, and also encourages the model to learn
relative rates of energy buildup in the harmonic partials of different
instruments. Experiments show salient performance improvement over baseline
methods. We also report an analysis probing how pitch information helps the
instrument prediction task. Code and experiment details can be found at
https://biboamy.github.io/instrument-recognition/.

本文利用 MusicNet 数据集，建立并评估了一个卷积神经网络，实现基于帧级别标注的乐器识别，并尝试不同方法将音高信息融入模型，实现对于多乐器帧级别噪声的校准、乐器之间谐波比较分析等，实验结果表明相对于基线方法具有显著的性能提升。