2026 Frank K. Soong: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	52	5049	4910	681	676	359	11789

Frank K. Soong publication distribution in Computer Science in 2026

The chart shows the distribution of publications by all Research.com ranked scientists in the field of Computer Science in 2026. The highlighted bar marks where Frank K. Soong sits on this spectrum.

32 publications 991+

This scientist: 359 publications — 83rd percentile

83% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 991 publications or more.

Frank K. Soong D-index placement in Computer Science in 2026

The chart shows the D-index (discipline H-index) distribution of Computer Science scientists ranked by Research.com in 2026. The highlighted bar marks where Frank K. Soong sits on this spectrum.

30 D-Index 131+

This scientist: 52 D-Index — 65th percentile

65% of scientists in this discipline score the same or lower.

The last bar groups every scientist with 131 D-Index or more.

Research.com Recognitions

2010 - IEEE Fellow For contributions to speech processing

Overview

Frank K. Soong is affiliated with Microsoft Research Asia (China) and has made significant contributions to the field of computer science, particularly in speech and audio processing. Their research spans a wide range of topics centered on speech recognition and synthesis, along with natural language processing techniques and cognitive neuroscience aspects related to EEG and brain-computer interfaces.

Their main fields of study include:

Computer Science

Within computer science, their subfields of study are:

Artificial Intelligence
Signal Processing
Experimental and Cognitive Psychology
Cognitive Neuroscience
Computer Vision and Pattern Recognition

The primary topics of their work cover the following areas:

Speech Recognition and Synthesis
Speech and Audio Processing
Natural Language Processing Techniques
Music and Audio Processing
Topic Modeling
Phonetics and Phonology Research
EEG and Brain-Computer Interfaces

Frequent coauthors collaborating with Soong include:

Lei He
Lei Xie
Shaoguang Mao
Xi Wang
Tao Qin

They have published extensively in notable venues, with frequent contributions to:

arXiv (Cornell University)
IEEE/ACM Transactions on Audio Speech and Language Processing
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Neural Networks
Interspeech 2022

Some of the recent papers authored or coauthored by Frank K. Soong include:

"A Survey on Neural Speech Synthesis," 2021, arXiv (Cornell University)
"NaturalSpeech: End-to-End Text-to-Speech Synthesis With Human-Level Quality," 2024, IEEE Transactions on Pattern Analysis and Machine Intelligence
"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality," 2022, arXiv (Cornell University)
"Dual-Threshold-Based Microstate Analysis on Characterizing Temporal Dynamics of Affective Process and Emotion Recognition From EEG Signals," 2021, Frontiers in Neuroscience
"Cycle consistent network for end-to-end style transfer TTS training," 2021, Neural Networks

Frank K. Soong was recognized as an IEEE Fellow in 2010 for contributions to speech processing.

Best Publications

Line spectrum pair (LSP) and speech data compression

F. Soong;B. Juang

646
Citations
TTS Synthesis with Bidirectional LSTM based Recurrent Neural Networks

Yuchen Fan;Yao Qian;Feng-Long Xie;Frank K. Soong

574
Citations
High performance connected digit recognition using hidden Markov models

L.R. Rabiner;J.G. Wilpon;F.K. Soong

391
Citations
Automatic Speech and Speaker Recognition: Advanced Topics

Chin-Hui Lee;Frank K. Soong;Kuldip K. Paliwal

282
Citations
A Tree.Trellis Based Fast Search for Finding the N Best Sentence Hypotheses in Continuous Speech Recognition

Unknown

272
Citations
Voice persona service for embedding text-to-speech features into software programs

Yusheng Li;Min Chu;Xin Zou;Frank Kao-Ping Soong

266
Citations
Identifying language of origin for words using estimates of normalized appearance frequency

Yi Ning Chen;Min Chu;Jiali You;Frank Kao-Ping Soong

264
Citations
The use of cohort normalized scores for speaker verification

Unknown

252
Citations
On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis

Yao Qian;Yuchen Fan;Wenping Hu;Frank K. Soong

249
Citations
Handwriting-based user interface for correction of speech recognition errors

Lijuan Wang;Frank Kao-Ping Soong

237
Citations
Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers

Wenping Hu;Wenping Hu;Yao Qian;Frank K. Soong;Yong Wang

234
Citations
Unnatural prosody detection in speech synthesis

Yong Zhao;Frank Kao-Ping Soong;Min Chu;Lijuan Wang

229
Citations
Optimal quantization of LSP parameters

F.K. Soong;B.-H. Juang

219
Citations
Automatic Speech and Speaker Recognition

Chin-Hui Lee;Frank K. Soong;Kuldip K. Paliwal

204
Citations
Report: A vector quantization approach to speaker recognition

Frank K. Soong;Aaron E. Rosenberg;Bling-Hwang Juang;Lawrence R. Rabiner

188
Citations
A Survey on Neural Speech Synthesis.

Xu Tan;Tao Qin;Frank K. Soong;Tie-Yan Liu

185
Citations
A high quality subband speech coder with backward adaptive predictor and optimal time-frequency bit assignment

F. Soong;R. Cox;N. Jayant

184
Citations
Cepstral channel normalization techniques for HMM-based speaker verification.

Aaron E. Rosenberg;Chin-Hui Lee;Frank K. Soong

173
Citations
Comparative study of several distortion measures for speech recognition

N. Nocerino;F. Soong;L. Rabiner;D. Klatt

167
Citations
On the automatic segmentation of speech signals

Unknown

166
Citations
A segment model based approach to speech recognition

Chin-Hui Lee;F.K. Soong;Bing-Hwang Juang

162
Citations
Evaluation of a vector quantization talker recognition system in text independent and text dependent modes

A.E. Rosenberg;F.K. Soong

160
Citations
Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis

Yuchen Fan;Yao Qian;Frank K. Soong;Lei He

148
Citations
Voice Activity Detection Based on an Unsupervised Learning Framework

Dongwen Ying;Yonghong Yan;Jianwu Dang;F. K. Soong

144
Citations

Frequent Co-Authors

Lei He University of California, Los Angeles

Hui Jiang York University

Chin-Hui Lee Georgia Institute of Technology

Helen Meng Chinese University of Hong Kong

Hai Zhao Shanghai Jiao Tong University

Jun Du University of Science and Technology of China

Li-Rong Dai University of Science and Technology of China

Satoshi Nakamura Nara Institute of Science and Technology

Aaron E. Rosenberg AT&T (United States)

Biing-Hwang Juang Georgia Institute of Technology

External Links

Personal website of Frank K. Soong

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Exploring computer science in the US opens up a variety of education and career options, including flexible pathways through online learning. Many online associate degree programs offer a solid foundation in computer science and IT, making them perfect for students looking to start their tech journey or transfer to a four-year university later.

For those concerned about costs, several of the cheapest online colleges deliver quality computer science education at a fraction of regular tuition fees. Affordability and flexibility make these programs ideal for working adults or anyone needing to balance study and life commitments.

If your academic record isn't perfect, don't worry—there are college with low gpa admission options, ensuring that motivated students can still access solid training and future opportunities in tech.

Beyond traditional tech jobs, a computer science background can also lead to unique industries. For example, combining computing with sustainability lets you explore “what can i do with an environmental science degree” and related interdisciplinary careers.