mlsanityData to 14 Oct 2026

mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra

arXiv 2305.11104 ↗First posted 18 May 2023eess.AS cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Speech super-resolution (SSR) aims to recover a high resolution (HR) speech from its corresponding low resolution (LR) counterpart. Recent SSR methods focus more on the reconstruction of the magnitude spectrogram, ignoring the importance of phase reconstruction, thereby limiting the recovery quality. To address this issue, we propose mdctGAN, a novel SSR framework based on modified discrete cosine transform (MDCT). By adversarial learning in the MDCT domain, our method reconstructs HR speeches in a phase-aware manner without vocoders or additional post-processing. Furthermore, by learning frequency consistent features with self-attentive mechanism, mdctGAN guarantees a high quality speech reconstruction. For VCTK corpus dataset, the experiment results show that our model produces natural auditory quality with high MOS and PESQ scores. It also achieves the state-of-the-art log-spectral-distance (LSD) performance on 48 kHz target resolution from various input rates. Code is available from https://github.com/neoncloud/mdctGAN

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 18 of its 22 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

18 of 22 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  4. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  5. 2017Mixed Precision Trainingcited by 1,156
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  7. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  8. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 141
  9. 2021Hi-Fi Multi-Speaker English TTS Datasetcited by 60
  10. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  11. 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
  12. 2022NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Ratescited by 36
6 more
  1. 2017Audio Super Resolution using Neural Networkscited by 26
  2. 2021DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancementcited by 23
  3. 2022Conditioning and Sampling in Variational Diffusion Models for Speech Super-Resolutioncited by 20
  4. 2021WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolutioncited by 19
  5. 2021Self-Attention for Audio Super-Resolutioncited by 9
  6. 2022Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling CycleGANscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 2.

6 papers.

  1. 2025Audio Super-Resolution with Latent Bridge Modelscited by 14
  2. 2025A2SB: Audio-to-Audio Schrodinger Bridgescited by 11
  3. 2024Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensorscited by 5
  4. 2026CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Spacecited by 1
  5. 2026LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matchingcited by 1
  6. 2025CogSR: Semantic-Aware Speech Super-Resolution via Chain-of-Thought Guided Flow Matchingcited by 0