Search Results for author: Xinwei Li

Found 4 papers, 0 papers with code

Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems

no code implementations7 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.

Data Augmentation End-To-End Speech Recognition

Automatic marker-free registration of tree point-cloud data based on rotating projection

no code implementations30 Jan 2020 Xiuxian Xu, Pei Wang, Xiaozheng Gan, Ya-Xin Li, Li Zhang, Qing Zhang, Mei Zhou, Yinghui Zhao, Xinwei Li

In coarse registration, point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional (2D) images, which are used to estimate the initial positions of multiple scans.

Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR

no code implementations8 Jul 2019 Felix Weninger, Jesús Andrés-Ferrer, Xinwei Li, Puming Zhan

Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the-art performances while having clear advantages in terms of simplicity.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.