Kai Yu

7.9k citations

283 papers · 4.6k indexed · 1 hit paper · h-index 35

Impact in

Signal Processing top 0.2%
- Speech and Audio Processing
- Music and Audio Processing
Artificial Intelligence top 0.2%
- Speech Recognition and Synthesis
- Topic Modeling
- Speech and dialogue systems
- Natural Language Processing Techniques
- Multi-Agent Systems and Negotiation

Papers in ⓘ

Artificial Intelligence 229
- Speech Recognition and Synthesis 137
- Topic Modeling 75
- Natural Language Processing Techniques 70
- Speech and dialogue systems 68
- Multi-Agent Systems and Negotiation 20
Signal Processing 122
- Speech and Audio Processing 107
- Music and Audio Processing 89

Co-authors: Yanmin Qian (50 shared papers)Steve Young (16 shared papers)Su Zhu (29 shared papers)François Mairesse (20 shared papers)Tian Tan (7 shared papers)Simon Keizer (19 shared papers)Milica Gašić (10 shared papers)Shuai Wang (14 shared papers)
Journals: IEEE/ACM Transactions on Audio Speech and Language Processing (20 papers)Speech Communication (6 papers)IEEE Transactions on Audio Speech and Language Processing (4 papers)Applied Sciences (3 papers)Redox Report (1 paper)
Partner nations: China United Kingdom United States

In The Last Decade

Kai Yu

267 papers receiving 4.3k citations

Hit Papers

align trajectories log scale

Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition 2016 · 252 citations

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if any of the following hold:

it has ≥500 total citations;
it reaches ≥1.5× the top-1% citation threshold for papers in the same subfield and year (the threshold is the minimum needed to enter the top 1%, not the average within it);
it reaches the top citation threshold in at least one of its specific research topics.

2016 IEEE/ACM Transactions on Audio Speech and Language Processing

Peers

Countries citing papers authored by Kai Yu

Since Specialization

Citations

This map shows the geographic impact of Kai Yu's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Kai Yu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Kai Yu more than expected).

Fields of papers citing papers by Kai Yu

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Kai Yu. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Kai Yu. The network helps show where Kai Yu may publish in the future.

Co-authors

The 25 scholars most cited alongside Kai Yu, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Kai Yu Line = papers co-authored together Kai Yu links everyone, so they are left out of the graph.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Showing the 20 most-cited of 283 papers — load more, or switch the sort, to bring in the rest.

#	Work
1	The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management Computer Speech & Language ·Steve Young, Milica Gašić, Simon Keizer, François Mairesse, Jost Schatzmann, Blaise Thomson, Kai Yu	2009	268
2	Very Deep Convolutional Neural Networks for Noise Robust Speech Recognition IEEE/ACM Transactions on Audio Speech and Language Processing ·Yanmin Qian, Mengxiao Bi, Tian Tan, Kai Yu Hit paper breakdown →	2016	252
3	Towards a new generation of artificial intelligence in China Nature Machine Intelligence ·Fei Wu, Cewu Lu, Mingjie Zhu, Hao Chen, Jun Zhu, Kai Yu, Lei Li, Ming Li, Qianfeng Chen, Xi Li, Xudong Cao, Zhongyuan Wang, Zheng-Jun Zha, Yueting Zhuang, Yunhe Pan	2020	168
4	Deep feature for text-dependent speaker verification Speech Communication ·Yuan Liu, Yanmin Qian, Nanxin Chen, Tianfan Fu, Ya Zhang, Kai Yu	2015	113
5	Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition Xu Xiang, Shuai Wang, Houjun Huang, Yanmin Qian, Kai Yu	2019	96
6	Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks Proceedings of the AAAI Conference on Artificial Intelligence ·Lu Chen, Boer Lv, Chi Wang, Su Zhu, Bowen Tan, Kai Yu	2020	86
7	Continuous F0 Modeling for HMM Based Statistical Parametric Speech Synthesis IEEE Transactions on Audio Speech and Language Processing ·Kai Yu, Steve Young	2010	85
8	Discriminative spoken language understanding using word confusion networks Matthew Henderson, Milica Gašić, Blaise Thomson, Pirros Tsiakoulis, Kai Yu, Steve Young	2012	78
9	Reshaping deep neural network for fast decoding by node-pruning Tianxing He, Yuchen Fan, Yanmin Qian, Tian Tan, Kai Yu	2014	76
10	Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning Cambridge University Engineering Department Publications Database ·François Mairesse, Milica Gašić, Filip Jurčíček, Simon Keizer, Blaise Thomson, Kai Yu, Steve Young	2010	73
11	Towards Universal Dialogue State Tracking Liliang Ren, Kaige Xie, Chen Lü, Kai Yu	2018	71
12	LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations Ruisheng Cao, Lu Chen, Zhi Chen, Yanbin Zhao, Su Zhu, Kai Yu	2021	67
13	Multi-task learning for text-dependent speaker verification Nanxin Chen, Yanmin Qian, Kai Yu	2015	64
14	Angular Softmax for Short-Duration Text-independent Speaker Verification Zili Huang, Shuai Wang, Kai Yu	2018	63
15	Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk Filip Jurčíček, Simon Keizer, Milica Gašić, François Mairesse, B. Thomson, Kai Yu, Steve Young	2011	59
16	Robust deep feature for spoofing detection — the SJTU system for ASVspoof 2015 challenge Nanxin Chen, Yanmin Qian, Heinrich Dinkel, Bo Chen, Kai Yu	2015	57
17	Deep features for automatic spoofing detection Speech Communication ·Yanmin Qian, Nanxin Chen, Kai Yu	2016	56
18	Cluster adaptive training for deep neural network Tian Tan, Yanmin Qian, Maofan Yin, Yimeng Zhuang, Kai Yu	2015	49
19	Unsupervised training and directed manual transcription for LVCSR Speech Communication ·Kai Yu, Mark Gales, Lan Wang, Philip C. Woodland	2010	48
20	Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding Su Zhu, Kai Yu	2017	47

About Kai Yu

Kai Yu is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Computer Networks and Communications and Information Systems, having authored 283 papers that have together received 4.6k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (137 papers), Speech and Audio Processing (107 papers), Music and Audio Processing (89 papers), Topic Modeling (75 papers), Natural Language Processing Techniques (70 papers), Speech and dialogue systems (68 papers), Multi-Agent Systems and Negotiation (20 papers) and Multimodal Machine Learning Applications (10 papers). The work is most often cited by research in Signal Processing (1.9k citations), Artificial Intelligence (3.8k citations), Computer Vision and Pattern Recognition (574 citations), Health Informatics (27 citations) and Experimental and Cognitive Psychology (159 citations). Kai Yu has collaborated with scholars based in China, United Kingdom and United States. Frequent co-authors include Yanmin Qian, Steve Young, Su Zhu, François Mairesse, Tian Tan, Simon Keizer, Milica Gašić, Shuai Wang, Blaise Thomson and Heinrich Dinkel. Their work appears in journals such as IEEE/ACM Transactions on Audio Speech and Language Processing, Speech Communication, IEEE Transactions on Audio Speech and Language Processing, Applied Sciences and Redox Report.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact