no code implementations • CVPR 2014 • Shuang Wu, Sravanthi Bondugula, Florian Luisier, Xiaodan Zhuang, Pradeep Natarajan
Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples.
no code implementations • 4 Oct 2019 • Zhen Huang, Tim Ng, Leo Liu, Henry Mason, Xiaodan Zhuang, Daben Liu
The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN).
no code implementations • 7 Dec 2020 • Xinwei Li, Yuanyuan Zhang, Xiaodan Zhuang, Daben Liu
We demonstrate that f-SpecAugment is more effective than the utterance level SpecAugment for deep CNN based hybrid models.
no code implementations • 27 Aug 2021 • Zhen Huang, Xiaodan Zhuang, Daben Liu, Xiaoqiang Xiao, Yuchen Zhang, Sabato Marco Siniscalchi
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
no code implementations • 2 Nov 2022 • Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang
This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios.
no code implementations • 18 Apr 2023 • Maurits Bleeker, Pawel Swietojanski, Stefan Braun, Xiaodan Zhuang
By including approximate nearest neighbour phrases (ANN-P) in the context list, we encourage the learned representation to disambiguate between similar, but not identical, biasing phrases.