mlsanityData to 14 Oct 2026

CIS-BWE: Chaos-Informed Speech Bandwidth Extension

arXiv 2507.15970 ↗First posted 21 Jul 2025cs.SD cs.AI eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Recovering high-frequency components lost to bandwidth constraints is crucial for applications ranging from telecommunications to high-fidelity audio on limited resources. We introduce NDSI-BWE, a new adversarial Band Width Extension (BWE) framework that leverage four new discriminators inspired by nonlinear dynamical system to capture diverse temporal behaviors: a Multi-Resolution Lyapunov Discriminator (MRLD) for determining sensitivity to initial conditions by capturing deterministic chaos, a Multi-Scale Recurrence Discriminator (MS-RD) for self-similar recurrence dynamics, a Multi-Scale Detrended Fractal Analysis Discriminator (MSDFA) for long range slow variant scale invariant relationship, a Multi-Resolution Poincar'e Plot Discriminator (MR-PPD) for capturing hidden latent space relationship, a Multi-Period Discriminator (MPD) for cyclical patterns, a Multi-Resolution Amplitude Discriminator (MRAD) and Multi-Resolution Phase Discriminator (MRPD) for capturing intricate amplitude-phase transition statistics. By using depth-wise convolution at the core of the convolutional block with in each discriminators, NDSI-BWE attains an eight-times parameter reduction. These seven discriminators guide a complex-valued ConformerNeXt based genetor with a dual stream Lattice-Net based architecture for simultaneous refinement of magnitude and phase. The genertor leverage the transformer based conformer's global dependency modeling and ConvNeXt block's local temporal modeling capability. Across six objective evaluation metrics and subjective based texts comprises of five human judges, NDSI-BWE establishes a new SoTA in BWE.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 66 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

29 of 66 references.

References · 29

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  3. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  4. 2018SDR - half-baked or well done?cited by 423
  5. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  6. 2018Adversarial Audio Synthesiscited by 225
  7. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 192
  8. 2019An Exponential Learning Rate Schedule for Deep Learningcited by 121
  9. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  10. 2021UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generationcited by 74
  11. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  12. 2019PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Networkcited by 51
17 more
  1. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  2. 2021Fre-GAN: Adversarial Frequency-consistent Audio Synthesiscited by 24
  3. 2022AERO: Audio Super Resolution in the Spectral Domaincited by 17
  4. 2021An Improved Model for Voicing Silent Speechcited by 15
  5. 2024Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Predictioncited by 14
  6. 2023Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancementcited by 13
  7. 2020TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesiscited by 11
  8. 2024TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platformscited by 11
  9. 2024VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoderscited by 10
  10. 2019Generative adversarial network-based glottal waveform model for statistical parametric speech synthesiscited by 7
  11. 2022EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient body-conduction microphonescited by 5
  12. 2018Reducing over-smoothness in speech synthesis using Generative Adversarial Networkscited by 4
  13. 2024Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Controlcited by 3
  14. 2022AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabularycited by 2
  15. 2024A lightweight and robust method for blind wideband-to-fullband extension of speechcited by 1
  16. 2025A High-Fidelity Speech Super Resolution Network using a Complex Global Attention Module with Spectro-Temporal Losscited by 1
  17. 2025An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancementcited by 1

Built on by

Not cited yet.