mlsanityData to 7 Oct 2026

SubSpectral Normalization for Neural Audio Data Processing

arXiv 2103.13620 ↗First posted 25 Mar 2021cs.SD cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks are widely used in various machine learning domains. In image processing, the features can be obtained by applying 2D convolution to all spatial dimensions of the input. However, in the audio case, frequency domain input like Mel-Spectrogram has different and unique characteristics in the frequency dimension. Thus, there is a need for a method that allows the 2D convolution layer to handle the frequency dimension differently. In this work, we introduce SubSpectral Normalization (SSN), which splits the input frequency dimension into several groups (sub-bands) and performs a different normalization for each group. SSN also includes an affine transformation that can be applied to each group. Our method removes the inter-frequency deflection while the network learns a frequency-aware characteristic. In the experiments with audio data, we observed that SSN can efficiently improve the network's performance.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

17 of 21 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Layer Normalizationcited by 5,579
  5. 2018Group Normalizationcited by 1,514
  6. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  7. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  8. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  9. 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 84
  10. 2018A multi-device dataset for urban acoustic scene classificationcited by 75
  11. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  12. 2019Temporal Convolution for Real-time Keyword Spotting on Mobile Devicescited by 48
5 more
  1. 2017Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LMcited by 43
  2. 2019The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classificationcited by 22
  3. 2018SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classificationcited by 10
  4. 2018EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edgecited by 5
  5. 2019Sub-band Convolutional Neural Networks for Small-footprint Spoken Term Classificationcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 0; 2024: 2; 2025: 4.

11 papers.

  1. 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 47
  2. 2022QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient designcited by 10
  3. 2021Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalizationcited by 4
  4. 2022Avoid Overfitting User Specific Information in Federated Keyword Spottingcited by 4
  5. 2024Phase-driven Domain Generalizable Learning for Nonstationary Time Seriescited by 4
  6. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  7. 2025Real-Time Streaming Mel Vocoding with Generative Flow Matchingcited by 1
  8. 2022A Temporal-oriented Broadcast ResNet for COVID-19 Detectioncited by 0
  9. 2024Advancing Airport Tower Command Recognition: Integrating Squeeze-and-Excitation and Broadcasted Residual Learningcited by 0
  10. 2025Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANscited by 0
  11. 2025Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theoremcited by 0