activity
20172022
most citedIntegrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling

67 citations · 87 across the 13 of their papers we have counts for

collaborators

12 papers

cs.CL2021

Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable

Ruiliu Fu, Han Wang, Xuejun Zhang +2

Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine reasoning pr…

cs.CL2021

Reminding the Incremental Language Model via Data-Free Self-Distillation

Han Wang, Ruiliu Fu, Chengzhang Li +3

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands f…

cs.SD20212 cited

The HCCL Speaker Verification System for Far-Field Speaker Verification Challenge

Zhuo Li, Ce Fang, Runqiu Xiao +3

This paper describes the systems submitted by team HCCL to the Far-Field Speaker Verification Challenge. Our previous work in the AIshell Speaker Verification Challenge 2019 shows…

eess.AS20218 cited

Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search

Yukun Liu, Ta Li, Pengyuan Zhang +1

Recently neural architecture search(NAS) has been successfully used in image classification, natural language processing, and automatic speech recognition(ASR) tasks for finding th…

eess.AS20201 cited

Multi-Accent Adaptation based on Gate Mechanism

Han Zhu, Li Wang, Pengyuan Zhang +1

When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, wh…

cs.SD2020

A Model Compression Method with Matrix Product Operators for Speech Enhancement

Xingwei Sun, Ze-Feng Gao, Zhong-Yi Lu +2

The deep neural network (DNN) based speech enhancement approaches have achieved promising performance. However, the number of parameters involved in these methods is usually enormo…