no code implementations • CCL 2020 • Pengfei Chen, Lina Wang, Hui Di, Kazushige Ouchi, Lvhong Wang
In contrast to existing quantization with low precision data format and projection layer, we propose a novel method based on shared labels, which focuses on compressing the fully-connected layer before Softmax for models with a huge number of labels in TTS polyphone selection.
no code implementations • Findings (EMNLP) 2021 • Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, Jinan Xu
Generative conversation systems tend to produce meaningless and generic responses, which significantly reduce the user experience.