FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation

no code implementations • 13 May 2024 • Jianyi Chen, Wei Xue, Xu Tan, Zhen Ye, Qifeng Liu, Yike Guo

By intensive experimental studies, we demonstrate that the proposed method can generate better samples than SingSong, and accelerate the generation by at least 30 times.

FlashSpeech: Efficient Zero-Shot Speech Synthesis

1 code implementation • 23 Apr 2024 • Zhen Ye, Zeqian Ju, Haohe Liu, Xu Tan, Jianyi Chen, Yiwen Lu, Peiwen Sun, Jiahao Pan, Weizhen Bian, Shulin He, Qifeng Liu, Yike Guo, Wei Xue

The generation processes of FlashSpeech can be achieved efficiently with one or two sampling steps while maintaining high audio quality and high similarity to the audio prompt for zero-shot speech generation.

Speech Synthesis Voice Conversion