Adversarial Audio Synthesis with Complex-valued Polynomial Networks
원문 초록
Time-frequency (TF) representations in audio synthesis have been increasingly modeled with real-valued networks. However, overlooking the complex-valued nature of TF representations can result in suboptimal performance and require additional modules (e.g., for modeling the phase). To this end, we introduce complex-valued polynomial networks, called APOLLO, that integrate such complex-valued representations in a natural way. Concretely, APOLLO captures high-order correlations of the input elements using high-order tensors as scaling parameters. By leveraging standard tensor decompositions, we derive different architectures and enable modeling richer correlations. We outline such architectures and showcase their performance in audio generation across four benchmarks. As a highlight, APOLLO results in $17.5\%$ improvement over adversarial methods and $8.2\%$ over the state-of-the-art diffusion models on SC09 dataset in audio generation. Our models can encourage the systematic design of other efficient architectures on the complex field.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis
LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis
AudioLCM: Text-to-Audio Generation with Latent Consistency Models
T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Neural Waveshaping Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.