Update info of DSFF-SVC (#278)

Update info of SVC paper

README.md

@@ -29,7 +29,7 @@
 In addition to the specific generation tasks, Amphion includes several **vocoders** and **evaluation metrics**. A vocoder is an important module for producing high-quality audio signals, while evaluation metrics are critical for ensuring consistent metrics in generation tasks. Moreover, Amphion is dedicated to advancing audio generation in real-world applications, such as building **large-scale datasets** for speech synthesis.
 
 ## 🚀 News
-- **2024/09/01**: [Amphion](https://arxiv.org/abs/2312.09911) and [Emilia](https://arxiv.org/abs/2407.05361) got accepted by IEEE SLT 2024! 🤗
+- **2024/09/01**: [Amphion](https://arxiv.org/abs/2312.09911), [Emilia](https://arxiv.org/abs/2407.05361) and [DSFF-SVC](https://arxiv.org/abs/2310.11160) got accepted by IEEE SLT 2024! 🤗
 - **2024/08/28**: Welcome to join Amphion's [Discord channel](https://discord.com/invite/ZxxREr3Y) to stay connected and engage with our community!
 - **2024/08/20**: [SingVisio](https://arxiv.org/abs/2402.12660) got accepted by Computers & Graphics, [available here](https://www.sciencedirect.com/science/article/pii/S0097849324001936)! 🎉
 - **2024/08/27**: *The Emilia dataset is now publicly available!* Discover the most extensive and diverse speech generation dataset with 101k hours of in-the-wild speech data now at [![hf](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/amphion/Emilia-Dataset) or [![OpenDataLab](https://img.shields.io/badge/OpenDataLab-Dataset-blue)](https://opendatalab.com/Amphion/Emilia)! 👑👑👑
@@ -53,7 +53,7 @@ In addition to the specific generation tasks, Amphion includes several **vocoder
 
 ### SVC: Singing Voice Conversion
 
-- Ampion supports multiple content-based features from various pretrained models, including [WeNet](https://github.com/wenet-e2e/wenet), [Whisper](https://github.com/openai/whisper), and [ContentVec](https://github.com/auspicious3000/contentvec). Their specific roles in SVC has been investigated in our NeurIPS 2023 workshop paper. [![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2310.11160) [![code](https://img.shields.io/badge/README-Code-red)](egs/svc/MultipleContentsSVC)
+- Ampion supports multiple content-based features from various pretrained models, including [WeNet](https://github.com/wenet-e2e/wenet), [Whisper](https://github.com/openai/whisper), and [ContentVec](https://github.com/auspicious3000/contentvec). Their specific roles in SVC has been investigated in our SLT 2024 paper. [![arXiv](https://img.shields.io/badge/arXiv-Paper-<COLOR>.svg)](https://arxiv.org/abs/2310.11160) [![code](https://img.shields.io/badge/README-Code-red)](egs/svc/MultipleContentsSVC)
 - Amphion implements several state-of-the-art model architectures, including diffusion-, transformer-, VAE- and flow-based models. The diffusion-based architecture uses [Bidirectional dilated CNN](https://openreview.net/pdf?id=a-xFK8Ymz5J) as a backend and supports several sampling algorithms such as [DDPM](https://arxiv.org/pdf/2006.11239.pdf), [DDIM](https://arxiv.org/pdf/2010.02502.pdf), and [PNDM](https://arxiv.org/pdf/2202.09778.pdf). Additionally, it supports single-step inference based on the [Consistency Model](https://openreview.net/pdf?id=FmqFfMTNnv).
 
 ### TTA: Text to Audio

egs/svc/DiffComoSVC/README.md

@@ -5,7 +5,7 @@
 </div>
 <br>
 
-This is an implement of [Consistency Models](https://arxiv.org/abs/2303.01469) for accelerating diffusion-based singing voice conversion. The overall architecture follows "[Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (NeurIPS 2023 Workshop on Machine Learning for Audio), only a slightly modification is applied on acoustic model. Specifically,
+This is an implement of [Consistency Models](https://arxiv.org/abs/2303.01469) for accelerating diffusion-based singing voice conversion. The overall architecture follows "[Leveraging Diverse Semantic-based Audio Pretrained Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (2024 IEEE Spoken Language Technology Workshop), only a slightly modification is applied on acoustic model. Specifically,
 
 * The acoustic model is a conformer which generates a coarse spectrogram and a diffusion decoder based on Bidirectional Non-Causal Dilated CNN which polish the former spectrogram for better. This is similar to [CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model](https://comospeech.github.io/)
 * To accelerate diffusion model, we apply consistency distillation from [Consistency Models](https://arxiv.org/abs/2303.01469). For teacher model, the diffusion schedule of the diffusion decoder follows [karras diffusion](https://arxiv.org/abs/2206.00364). For distilling teacher model, the condition encoder and the conformer part of acoustic model are frozen while the diffusion decoder model is updated via exponential moving average. See Figure above for details.

egs/svc/MultipleContentsSVC/README.md

@@ -12,7 +12,7 @@
 </div>
 <br>
 
-This is the official implementation of the paper "[Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (NeurIPS 2023 Workshop on Machine Learning for Audio). Specially,
+This is the official implementation of the paper "[Leveraging Diverse Semantic-based Audio Pretrained Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (2024 IEEE Spoken Language Technology Workshop). Specially,
 
 - The muptile content features are from [Whipser](https://github.com/wenet-e2e/wenet) and [ContentVec](https://github.com/auspicious3000/contentvec).
 - The acoustic model is based on Bidirectional Non-Causal Dilated CNN (called `DiffWaveNetSVC` in Amphion), which is similar to [WaveNet](https://arxiv.org/pdf/1609.03499.pdf), [DiffWave](https://openreview.net/forum?id=a-xFK8Ymz5J), and [DiffSVC](https://ieeexplore.ieee.org/document/9688219).
@@ -239,10 +239,10 @@ sh egs/svc/MultipleContentsSVC/run.sh --stage 3 --gpu "0" \
 ## Citations
 
 ```bibtex
-@article{zhang2023leveraging,
-  title={Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion},
-  author={Zhang, Xueyao and Gu, Yicheng and Chen, Haopeng and Fang, Zihao and Zou, Lexiao and Xue, Liumeng and Wu, Zhizheng},
-  journal={Machine Learning for Audio Workshop, NeurIPS 2023},
-  year={2023}
+@inproceedings{zhang2024leveraging,
+    author={Zhang, Xueyao and Fang, Zihao and Gu, Yicheng and Chen, Haopeng and Zou, Lexiao and Zhang, Junan and Xue, Liumeng and Wu, Zhizheng},
+    title={Leveraging Diverse Semantic-based Audio Pretrained Models for Singing Voice Conversion},
+    booktitle={{IEEE} Spoken Language Technology Workshop, {SLT} 2024},
+    year={2024}
 }
 ```

egs/svc/README.md

@@ -2,7 +2,7 @@
 
 ## Quick Start
 
-We provide a **[beginner recipe](MultipleContentsSVC)** to demonstrate how to train a cutting edge SVC model. Specifically, it is also an official implementation of the paper "[Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (NeurIPS 2023 Workshop on Machine Learning for Audio). Some demos can be seen [here](https://www.zhangxueyao.com/data/MultipleContentsSVC/index.html).
+We provide a **[beginner recipe](MultipleContentsSVC)** to demonstrate how to train a cutting edge SVC model. Specifically, it is also an official implementation of the paper "[Leveraging Diverse Semantic-based Audio Pretrained Models for Singing Voice Conversion](https://arxiv.org/abs/2310.11160)" (2024 IEEE Spoken Language Technology Workshop). Some demos can be seen [here](https://www.zhangxueyao.com/data/MultipleContentsSVC/index.html).
 
 ## Supported Model Architectures