activity
20182021
most citedPanGu-: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

94 citations · 119 across the 8 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.LG202111 cited

Bilateral Denoising Diffusion Models

Max W. Y. Lam, Jun Wang, Rongjie Huang +2

Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilater…

cs.SD20211 cited

Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition

Max W. Y. Lam, Jun Wang, Chao Weng +2

End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable…

cs.CL202194 cited

PanGu-: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation

Wei Zeng, Xiaozhe Ren, Teng Su +35

Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demon…

eess.AS20214 cited

Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation

Max W. Y. Lam, Jun Wang, Dan Su +1

One of the leading single-channel speech separation (SS) models is based on a TasNet with a dual-path segmentation technique, where the size of each segment remains unchanged throu…

eess.AS2021

Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect

Jun Wang, Max W. Y. Lam, Dan Su +1

We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns…

eess.AS2021

Contrastive Separative Coding for Self-supervised Representation Learning

Jun Wang, Max W. Y. Lam, Dan Su +1

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our…