mlsanityData to 14 Oct 2026

Deep neural network techniques for monaural speech enhancement: state of the art analysis

arXiv 2212.00369 ↗First posted 1 Dec 2022cs.SD cs.LG eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNN) techniques have become pervasive in domains such as natural language processing and computer vision. They have achieved great success in these domains in task such as machine translation and image generation. Due to their success, these data driven techniques have been applied in audio domain. More specifically, DNN models have been applied in speech enhancement domain to achieve denosing, dereverberation and multi-speaker separation in monaural speech enhancement. In this paper, we review some dominant DNN techniques being employed to achieve speech separation. The review looks at the whole pipeline of speech enhancement from feature extraction, how DNN based tools are modelling both global and local features of speech and model training (supervised and unsupervised). We also review the use of speech-enhancement pre-trained models to boost speech enhancement process. The review is geared towards covering the dominant trends with regards to DNN application in speech enhancement in speech obtained via a single speaker.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 132 of its 266 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

132 of 266 references.

References · 132

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  8. 2020Longformer: The Long-Document Transformercited by 3,413
  9. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  10. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  11. 2017Improved Training of Wasserstein GANscited by 2,235
  12. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
38 more
  1. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  2. 2020Reformer: The Efficient Transformercited by 1,668
  3. 2020Knowledge Distillation: A Surveycited by 1,603
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  5. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  7. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  8. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  9. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  10. 2018SDR - half-baked or well done?cited by 423
  11. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  12. 2022Understanding Diffusion Models: A Unified Perspectivecited by 340
  13. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
  14. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  15. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  16. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 241
  17. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 216
  18. 2015Deep clustering: Discriminative embeddings for segmentation and separationcited by 212
  19. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 198
  20. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 191
  21. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 188
  22. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 186
  23. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  24. 2020Attention is All You Need in Speech Separationcited by 185
  25. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  26. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
  27. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  28. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  29. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  30. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  31. 2017Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networkscited by 98
  32. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 75
  33. 2018VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Maskingcited by 73
  34. 2020Vector-Quantized Autoregressive Predictive Codingcited by 69
  35. 2020Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separationcited by 68
  36. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Modelcited by 53
  37. 2020Sudo rm -rf: Efficient Networks for Universal Audio Source Separationcited by 51
  38. 2017A Wavenet for Speech Denoisingcited by 47

50 most cited of 132 All 132 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy Referencescited by 4
  2. 2024Multiple Choice Learning for Efficient Speech Separation with Many Speakerscited by 3
  3. 2025On the Application of Diffusion Models for Simultaneous Denoising and Dereverberationcited by 0