no code implementations • 30 Nov 2023 • Miao Zhang, Peng Jia, Zhengyang Li, Wennan Xiang, Jiameng Lv, Rui Sun
To address this, we need a method to obtain misalignment states, aiding in the reconstruction of accurate point spread functions for data processing methods or facilitating adjustments of optical components for improved image quality.
1 code implementation • 20 Sep 2022 • Timo Lohrenz, Björn Möller, Zhengyang Li, Tim Fingscheidt
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models.
Ranked #3 on Lipreading on LRS3-TED (using extra training data)
no code implementations • 26 May 2022 • Zhengyang Li, Shijing Si, Jianzong Wang, Jing Xiao
To address this issue, we propose a framework, FedSplitBERT, which handles heterogeneous data and decreases the communication cost by splitting the BERT encoder layers into local part and global part.
no code implementations • 9 May 2022 • Ernst Seidel, Rasmus Kongsgaard Olsson, Karim Haddad, Zhengyang Li, Pejman Mowlaee, Tim Fingscheidt
Although today's speech communication systems support various bandwidths from narrowband to super-wideband and beyond, state-of-the art DNN methods for acoustic echo cancellation (AEC) are lacking modularity and bandwidth scalability.
1 code implementation • 2 Jul 2021 • Timo Lohrenz, Patrick Schwarz, Zhengyang Li, Tim Fingscheidt
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks.
Ranked #7 on Speech Recognition on WSJ eval92
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 31 Mar 2021 • Timo Lohrenz, Zhengyang Li, Tim Fingscheidt
Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model architectures.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 20 Nov 2020 • Peng Jia, Xuebo Wu, Zhengyang Li, Bo Li, Weihua Wang, Qiang Liu, Adam Popowicz
Then we use these data to train a DNN (Tel--Net).
no code implementations • 31 Jan 2020 • Peng Jia, Xiyu Li, Zhengyang Li, Weinan Wang, Dongmei Cai
For wide field small aperture telescopes, the point spread function is hard to model, because it is affected by many different effects and has strong temporal and spatial variations.