43 citations · 47 across the 5 of their papers we have counts for
5 papers
Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module
Zhongjian Cui, Chenrui Cui, Tianrui Wang +6
The information loss or distortion caused by single-channel speech enhancement (SE) harms the performance of automatic speech recognition (ASR). Observation addition (OA) is an eff…
VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
Yongmao Zhang, Heyang Xue, Hanzhao Li +4
End-to-end singing voice synthesis (SVS) model VISinger can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problem…
A Post Auto-regressive GAN Vocoder Focused on Spectrum Fracture
Zhenxing Lu, Mengnan He, Ruixiong Zhang +1
Generative adversarial networks (GANs) have been indicated their superiority in usage of the real-time speech synthesis. Nevertheless, most of them make use of deep convolutional l…
Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data
Zhu Li, Yuqing Zhang, Mengxi Nie +4
Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high…
Towards End-to-End Code-Switching Speech Recognition
Ne Luo, Dongwei Jiang, Shuaijiang Zhao +3
Code-switching speech recognition has attracted an increasing interest recently, but the need for expert linguistic knowledge has always been a big issue. End-to-end automatic spee…