mlsanityData to 7 Oct 2026

SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Features

arXiv 2108.03020 ↗First posted 6 Aug 2021cs.SDcited by 30

Not on the map. Why?

Abstract (arXiv)

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to be effective in improving image classification performance, their efficacy toward time-frequency domain features of audio is not assured. We propose a novel audio data augmentation approach named "Specmix" specifically designed for dealing with time-frequency domain features. The augmentation method consists of mixing two different data samples by applying time-frequency masks effective in preserving the spectral correlation of each audio sample. Our experiments on acoustic scene classification, sound event classification, and speech enhancement tasks show that the proposed Specmix improves the performance of various neural network architectures by a maximum of 2.7%.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Aug 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 9; 2025: 4; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  2. 2022A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspectivecited by 27
  3. 2023Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learningcited by 18
  4. 2022Frequency Selective Augmentation for Video Representation Learningcited by 3
  5. 2023MPE4G: Multimodal Pretrained Encoder for Co-Speech Gesture Generationcited by 3
  6. 2023AudRandAug: Random Image Augmentations for Audio Classificationcited by 3
  7. 2023Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Datacited by 3
  8. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  9. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  10. 2023PowMix: A Versatile Regularizer for Multimodal Sentiment Analysiscited by 1
  11. 2024Generative AI-based data augmentation for improved bioacoustic classification in noisy environmentscited by 1
  12. 2025Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentationcited by 1
18 more
  1. 2025Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversioncited by 1
  2. 2025MultiDiffNet: A Multi-Objective Diffusion Framework for Generalizable Brain Decodingcited by 1
  3. 2023Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detectioncited by 0
  4. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  5. 2023GMTR: Graph Matching Transformerscited by 0
  6. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  7. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  8. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  9. 2024StiefelGen: A Simple, Model Agnostic Approach for Time Series Data Augmentation over Riemannian Manifoldscited by 0
  10. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  11. 2024Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminatorcited by 0
  12. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  13. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  14. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  15. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  16. 2026"OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detectioncited by 0
  17. 2026Advancing Speaker-Based Vocal Effort Classification with WavLM and Data Augmentation in Naturalistic Non-Calibrated Speech Recordingscited by 0
  18. 2026NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environmentscited by 0