FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913199539879936 |
|---|---|
| author | Nguyen, Tan Dat Kim, Ji-Hoon Jang, Youngjoon Kim, Jaehun Chung, Joon Son |
| author_facet | Nguyen, Tan Dat Kim, Ji-Hoon Jang, Youngjoon Kim, Jaehun Chung, Joon Son |
| contents | The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes a complicated waveform into sub-band wavelets, which helps FreGrad to operate on a simple and concise feature space, (2) We design a frequency-aware dilated convolution that elevates frequency awareness, resulting in generating speech with accurate frequency information, and (3) We introduce a bag of tricks that boosts the generation quality of the proposed model. In our experiments, FreGrad achieves 3.7 times faster training time and 2.2 times faster inference speed compared to our baseline while reducing the model size by 0.6 times (only 1.78M parameters) without sacrificing the output quality. Audio samples are available at: https://mm.kaist.ac.kr/projects/FreGrad. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10032 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder Nguyen, Tan Dat Kim, Ji-Hoon Jang, Youngjoon Kim, Jaehun Chung, Joon Son Audio and Speech Processing Artificial Intelligence Signal Processing The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key components: (1) We employ discrete wavelet transform that decomposes a complicated waveform into sub-band wavelets, which helps FreGrad to operate on a simple and concise feature space, (2) We design a frequency-aware dilated convolution that elevates frequency awareness, resulting in generating speech with accurate frequency information, and (3) We introduce a bag of tricks that boosts the generation quality of the proposed model. In our experiments, FreGrad achieves 3.7 times faster training time and 2.2 times faster inference speed compared to our baseline while reducing the model size by 0.6 times (only 1.78M parameters) without sacrificing the output quality. Audio samples are available at: https://mm.kaist.ac.kr/projects/FreGrad. |
| title | FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder |
| topic | Audio and Speech Processing Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2401.10032 |