A Post Auto-regressive GAN Vocoder Focused On Spectrum Fracture

Abstract

Generative adversarial networks (GANs) have been indicated their superiority in usage of the real-time speech synthesis. Nevertheless, most of them make use of deep convolutional layers as their backbone, which may cause the absence of previous signal information. However, the generation of speech signals invariably require preceding waveform samples in its reconstruction, as the lack of this can lead to artifacts in generated speech. To address this conflict, in this paper, we propose an improved model: a post auto-regressive (AR) GAN vocoder with a self-attention layer, which merging self-attention in an AR loop. It will not participate in inference, but can assist the generator to learn temporal dependencies within frames in training. Furthermore, an ablation study was done to confirm the contribution of each part. Systematic experiments show that our model leads to a consistent improvement on both objective and subjective evaluation performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2022a

Related papers

• Avocodo: Generative Adversarial Network For Artifact-free Vocoder (2022)9.41
• Analysis By Adversarial Synthesis -- A Novel Approach For Speech Vocoding (2019)3.58
• Parallel Synthesis For Autoregressive Speech Generation (2022)4.52
• TFGAN: Time And Frequency Domain Based Generative Adversarial Network For High-fidelity Speech Synthesis (2020)0.00
• Vnet: A Gan-based Multi-tier Discriminator Network For Speech Synthesis Vocoders (2024)2.26
• Dynamic Attention Based Generative Adversarial Network With Phase Post-processing For Speech Enhancement (2020)0.00
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• A Multi-scale Time-frequency Spectrogram Discriminator For Gan-based Non-autoregressive TTS (2022)6.77