mlsanityData to 7 Oct 2026

SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling

arXiv 2506.22321 ↗First posted 27 Jun 2025cs.SD cs.AI eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Hearables are wearable computers that are worn on the ear. Bone conduction microphones (BCMs) are used with air conduction microphones (ACMs) in hearables as a supporting modality for multimodal speech enhancement (SE) in noisy conditions. However, existing works don't consider the following practical aspects for low-power implementations on hearables: (i) They do not explore how lowering the sampling frequencies and bit resolutions in analog-to-digital converters (ADCs) of hearables jointly impact low-power processing and multimodal SE in terms of speech quality and intelligibility. And (iii) They don't process signals from ACMs/BCMs at a sub-Nyquist sampling rate because, in their frameworks, they lack a wideband reconstruction methodology from their narrowband parts. We propose SUBARU (Sub-Nyquist Audio Resolution Upsampling), which achieves the following: SUBARU (i) intentionally uses sub-Nyquist sampling and low bit resolution in ADCs, achieving a 3.31x reduction in power consumption; and (ii) achieves streaming operations on mobile platforms and SE in in-the-wild noisy conditions with an inference time of 1.74ms and a memory footprint of less than 13.77MB.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 54 references that are in the map. First posted on arXiv 27 Jun 2025.

Builds on

31 of 54 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2016Layer Normalizationcited by 5,579
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  5. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  7. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  8. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  9. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  10. 2022Solving Audio Inverse Problems with a Diffusion Modelcited by 62
  11. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  12. 2019PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Networkcited by 49
19 more
  1. 2023AudioSR: Versatile Audio Super-resolution at Scalecited by 39
  2. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  3. 2019Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulationscited by 36
  4. 2022NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Ratescited by 36
  5. 2020SEANet: A Multi-modal Speech Enhancement Networkcited by 35
  6. 2017Audio Super Resolution using Neural Networkscited by 26
  7. 2020Real-time Speech Frequency Bandwidth Extensioncited by 22
  8. 2023Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approachcited by 21
  9. 2022AERO: Audio Super Resolution in the Spectral Domaincited by 17
  10. 2022BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networkscited by 13
  11. 2024A Diffusion-Based Generative Equalizer for Music Restorationcited by 12
  12. 2020NU-GAN: High resolution neural upsampling with GANcited by 11
  13. 2020TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesiscited by 11
  14. 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
  15. 2022Neural Speech Phase Prediction based on Parallel Estimation Architecture and Anti-Wrapping Lossescited by 10
  16. 2021Self-Attention for Audio Super-Resolutioncited by 9
  17. 2022EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient body-conduction microphonescited by 5
  18. 2024Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensorscited by 5
  19. 2021Enabling Real-time On-chip Audio Super Resolution for Bone Conduction Microphonescited by 4

Built on by

Not cited yet.