mlsanityData to 14 Oct 2026

MSR-NV: Neural Vocoder Using Multiple Sampling Rates

arXiv 2109.13714 ↗First posted 28 Sep 2021eess.AS cs.LG cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

The development of neural vocoders (NVs) has resulted in the high-quality and fast generation of waveforms. However, conventional NVs target a single sampling rate and require re-training when applied to different sampling rates. A suitable sampling rate varies from application to application due to the trade-off between speech quality and generation speed. In this study, we propose a method to handle multiple sampling rates in a single NV, called the MSR-NV. By generating waveforms step-by-step starting from a low sampling rate, MSR-NV can efficiently learn the characteristics of each frequency band and synthesize high-quality speech at multiple sampling rates. It can be regarded as an extension of the previously proposed NVs, and in this study, we extend the structure of Parallel WaveGAN (PWG). Experimental evaluation results demonstrate that the proposed method achieves remarkably higher subjective quality than the original PWG trained separately at 16, 24, and 48 kHz, without increasing the inference time. We also show that MSR-NV can leverage speech with lower sampling rates to further improve the quality of the synthetic speech.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 28 Sep 2021.

Builds on

23 of 32 references.

References · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  9. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  10. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  11. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  12. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
11 more
  1. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  2. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  3. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 215
  4. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 110
  5. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  6. 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
  7. 2020VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Networkcited by 26
  8. 2020Quasi-Periodic Parallel WaveGAN: A Non-autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Networkcited by 8
  9. 2020Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminatorscited by 7
  10. 2021PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic componentscited by 7
  11. 2021Improved parallel WaveGAN vocoder with perceptually weighted spectrogram losscited by 6

Built on by

Not cited yet.