mlsanityData to 7 Oct 2026

HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement

arXiv 2203.13086 ↗First posted 24 Mar 2022cs.SD cs.LG eess.AScited by 49

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models. In this paper, we show that this success can be extended to other tasks of conditional audio generation. In particular, building upon HiFi vocoders, we propose a novel HiFi++ general framework for bandwidth extension and speech enhancement. We show that with the improved generator architecture, HiFi++ performs better or comparably with the state-of-the-art in these tasks while spending significantly less computational resources. The effectiveness of our approach is validated through a series of extensive experiments.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 33 of its 60 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

33 of 60 references.

References · 33

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2018SDR - half-baked or well done?cited by 420
  9. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  10. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  11. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  12. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
21 more
  1. 2020Real Time Speech Enhancement in the Waveform Domaincited by 183
  2. 2021DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressorscited by 165
  3. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  4. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  5. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  6. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  7. 2019Music Source Separation in the Waveform Domaincited by 98
  8. 2018The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methodscited by 68
  9. 2016Generative Multi-Adversarial Networkscited by 60
  10. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  11. 2021Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separationcited by 48
  12. 2019Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulationscited by 36
  13. 2018Differentiable Consistency Constraints for Improved Deep Speech Enhancementcited by 35
  14. 2020SEANet: A Multi-modal Speech Enhancement Networkcited by 35
  15. 2017Audio Super Resolution using Neural Networkscited by 26
  16. 2020Real-time Speech Frequency Bandwidth Extensioncited by 22
  17. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancementcited by 18
  18. 2021GAN Vocoder: Multi-Resolution Discriminator Is All You Needcited by 16
  19. 2020TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesiscited by 11
  20. 2019Bandwidth Extension on Raw Audio via Generative Adversarial Networkscited by 10
  21. 2020On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networkscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 7; 2024: 9; 2025: 15; 2026: 14.

49 papers.

Sort:

By area:

  1. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  2. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  3. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  4. 2025EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judgecited by 24
  5. 2023Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approachcited by 21
  6. 2025FlowSE: Flow Matching-based Speech Enhancementcited by 20
  7. 2025InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-trainingcited by 11
  8. 2023Diffusion Posterior Sampling for Informed Single-Channel Dereverberationcited by 9
  9. 2024Meta Learning Text-to-Speech Synthesis in over 7000 Languagescited by 9
  10. 20241000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesiscited by 8
  11. 2023UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Modelcited by 7
  12. 2024FINALLY: fast and universal speech enhancement with studio-like qualitycited by 7
37 more
  1. 2025Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokenscited by 7
  2. 2025Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latencycited by 6
  3. 2022Iterative autoregression: a novel trick to improve your low-latency speech enhancement modelcited by 5
  4. 2023On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settingscited by 5
  5. 2024Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensorscited by 5
  6. 2024Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Examplecited by 5
  7. 2025Children's Voice Privacy: First Steps And Emerging Challengescited by 5
  8. 2025A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancementcited by 4
  9. 2025Robust One-step Speech Enhancement via Consistency Distillationcited by 4
  10. 2025VoiceBridge: General Speech Restoration with One-step Latent Bridge Modelscited by 4
  11. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  12. 2023In-the-wild Speech Emotion Conversion Using Disentangled Self-Supervised Representations and Neural Vocoder-based Resynthesiscited by 3
  13. 2023Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Modelcited by 3
  14. 2023Low-latency Real-time Voice Conversion on CPUcited by 3
  15. 2025Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learningcited by 3
  16. 2026Speech Enhancement Based on Drifting Modelscited by 2
  17. 2024Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbudscited by 1
  18. 2024Improving Voice Quality in Speech Anonymization With Just Perception-Informed Lossescited by 1
  19. 2025HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networkscited by 1
  20. 2025Real-Time Streaming Mel Vocoding with Generative Flow Matchingcited by 1
  21. 2026Time-Unconditional Generative Speech Enhancement via Autonomous Rectified Flowcited by 1
  22. 2026When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detectioncited by 1
  23. 2026The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speechcited by 1
  24. 2024DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translationcited by 0
  25. 2024Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generationcited by 0
  26. 2025Speech Enhancement based on cascaded two flowscited by 0
  27. 2025Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditionscited by 0
  28. 2026Lightweight and perceptually-guided voice conversion for electro-laryngeal speechcited by 0
  29. 2026Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergycited by 0
  30. 2026FastWave: Optimized Diffusion Model for Audio Super-Resolutioncited by 0
  31. 2026When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTScited by 0
  32. 2026Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?cited by 0
  33. 2026TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusioncited by 0
  34. 2026Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancementcited by 0
  35. 2026SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulationcited by 0
  36. 2026LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgishcited by 0
  37. 2026DriftSE: Speech Enhancement with Generative Driftingcited by 0