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

arXiv: https://arxiv.org/abs/2306.14191 · HTML: https://mlsanity.com/paper/2306.14191/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 16 of 16)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [Convolutional Recurrent Neural Networks for Music Classification](https://mlsanity.com/paper/1609.04243/) (2016)
- [Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization](https://mlsanity.com/paper/1912.04761/) (2019)
- [Analysis and Detection of Singing Techniques in Repertoires of J-POP Solo Singers](https://mlsanity.com/paper/2210.17367/) (2022)
- [Impact of Sound Duration and Inactive Frames on Sound Event Detection Performance](https://mlsanity.com/paper/2102.01927/) (2021)
- [Addressing the confounds of accompaniments in singer identification](https://mlsanity.com/paper/2002.06817/) (2020)
- [On The Differences Between Song and Speech Emotion Recognition: Effect of Feature Sets, Feature Types, and Classifiers](https://mlsanity.com/paper/2004.00200/) (2020)

## Built on by (most cited first, 1 of 1)

- [Recognizing Ornaments in Vocal Indian Art Music with Active Annotation](https://mlsanity.com/paper/2505.04419/) (2025)

## Abstract (arXiv)

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.