212 citations · 660 across the 46 of their papers we have counts for
4 papers · 1 filter
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Sang-gil Lee, Wei Ping, Boris Ginsburg +2
Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthe…
Factuality Enhanced Language Models for Open-Ended Text Generation
Nayeon Lee, Wei Ping, Peng Xu +4
Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open…
Speech Denoising in the Waveform Domain with Self-Attention
Zhifeng Kong, Wei Ping, Ambrish Dantrey +1
In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-a…
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Boxin Wang, Wei Ping, Chaowei Xiao +6
Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language m…