7 citations · 9 across the 3 of their papers we have counts for
4 papers
Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems
Xinwei Li, Yuanyuan Zhang, Xiaodan Zhuang +1
Inspired by SpecAugment -- a data augmentation method for end-to-end ASR systems, we propose a frame-level SpecAugment method (f-SpecAugment) to improve the performance of deep con…
Class LM and word mapping for contextual biasing in End-to-End ASR
Rongqing Huang, Ossama Abdel-hamid, Xinwei Li +1
In recent years, all-neural, end-to-end (E2E) ASR systems gained rapid interest in the speech recognition community. They convert speech input to text units in a single trainable N…
Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
Felix Weninger, Jesús Andrés-Ferrer, Xinwei Li +1
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity. However, comparisons are mostly done…
Demonstrating research subcommunities in mathematical networks
Steven B. Bradlow, Konstantinos Kapenekakis, Georgios Kydonakis +2
We propose a method for demonstrating sub community structure in scientific networks of relatively small size from analyzing databases of publications. Research relationships betwe…