# Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder

arXiv: https://arxiv.org/abs/2311.14957 · HTML: https://mlsanity.com/paper/2311.14957/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2023.

## Built on by (most cited first, 13 of 13)

- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [GenVC: Self-Supervised Zero-Shot Voice Conversion](https://mlsanity.com/paper/2502.04519/) (2025)
- [FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation](https://mlsanity.com/paper/2501.10807/) (2025)
- [UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation](https://mlsanity.com/paper/2503.00733/) (2025)
- [Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization](https://mlsanity.com/paper/2408.08019/) (2024)
- [Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation](https://mlsanity.com/paper/2512.23278/) (2025)
- [HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling](https://mlsanity.com/paper/2507.18897/) (2025)
- [EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks](https://mlsanity.com/paper/2402.00892/) (2024)
- [AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation](https://mlsanity.com/paper/2606.30811/) (2026)
- [AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing](https://mlsanity.com/paper/2609.08936/) (2026)
- [RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer](https://mlsanity.com/paper/2501.01182/) (2025)
- [EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization](https://mlsanity.com/paper/2507.06040/) (2025)
- [ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models](https://mlsanity.com/paper/2607.09134/) (2026)

## Abstract (arXiv)

Generative Adversarial Network (GAN) based vocoders are superior in inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator to promote GAN-based vocoders. Most existing time-frequency-representation-based discriminators are rooted in Short-Time Fourier Transform (STFT), whose time-frequency resolution in a spectrogram is fixed, making it incompatible with signals like singing voices that require flexible attention for different frequency bands. Motivated by that, our study utilizes the Constant-Q Transform (CQT), which owns dynamic resolution among frequencies, contributing to a better modeling ability in pitch accuracy and harmonic tracking. Specifically, we propose a Multi-Scale Sub-Band CQT (MS-SB-CQT) Discriminator, which operates on the CQT spectrogram at multiple scales and performs sub-band processing according to different octaves. Experiments conducted on both speech and singing voices confirm the effectiveness of our proposed method. Moreover, we also verified that the CQT-based and the STFT-based discriminators could be complementary under joint training. Specifically, enhanced by the proposed MS-SB-CQT and the existing MS-STFT Discriminators, the MOS of HiFi-GAN can be boosted from 3.27 to 3.87 for seen singers and from 3.40 to 3.78 for unseen singers.