Adversarial Generation Of Time-frequency Features With Application In Audio Synthesis

Abstract

Time-frequency (TF) representations provide powerful and intuitive features for the analysis of time series such as audio. But still, generative modeling of audio in the TF domain is a subtle matter. Consequently, neural audio synthesis widely relies on directly modeling the waveform and previous attempts at unconditionally synthesizing audio from neurally generated invertible TF features still struggle to produce audio at satisfying quality. In this article, focusing on the short-time Fourier transform, we discuss the challenges that arise in audio synthesis based on generated invertible TF features and how to overcome them. We demonstrate the potential of deliberate generative TF modeling by training a generative adversarial network (GAN) on short-time Fourier features. We show that by applying our guidelines, our TF-based network was able to outperform a state-of-the-art GAN generating waveforms directly, despite the similar architecture in the two networks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymarafioti2019adversarial

Related papers

• TFGAN: Time And Frequency Domain Based Generative Adversarial Network For High-fidelity Speech Synthesis (2020)0.00
• Gansynth: Adversarial Neural Audio Synthesis (2019)0.00
• High Fidelity Speech Synthesis With Adversarial Networks (2019)0.00
• Adversarial Audio Synthesis (2018)0.00
• Waveform Generation For Text-to-speech Synthesis Using Pitch-synchronous Multi-scale Generative Adversarial Networks (2018)8.35
• Exploiting Pre-trained Feature Networks For Generative Adversarial Networks In Audio-domain Loop Generation (2022)0.00
• Hifi-gan: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis (2020)0.00
• Melgan: Generative Adversarial Networks For Conditional Waveform Synthesis (2019)0.00