D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 33 Citations 6,422 245 World Ranking 6931 National Ranking 3290

Research.com Recognitions

Awards & Achievements

2010 - IEEE Fellow For contributions to speech processing

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Speech recognition
  • Statistics

His main research concerns Speech recognition, Artificial intelligence, Hidden Markov model, Natural language processing and Speech synthesis. His work deals with themes such as Artificial neural network, Recurrent neural network and Pronunciation, which intersect with Speech recognition. His Artificial intelligence study frequently intersects with other fields, such as Pattern recognition.

His Hidden Markov model research is multidisciplinary, incorporating perspectives in Parametric statistics, Face, Computer vision, Utterance and Mandarin Chinese. His Natural language processing study which covers Prosody that intersects with Viterbi algorithm and Pruning. The concepts of his Speech synthesis study are interwoven with issues in Persona, Service, Embedding, Morphing and Phrase.

His most cited work include:

  • TTS Synthesis with Bidirectional LSTM based Recurrent Neural Networks (315 citations)
  • Voice persona service for embedding text-to-speech features into software programs (187 citations)
  • Handwriting-based user interface for correction of speech recognition errors (165 citations)

What are the main themes of his work throughout his whole career to date?

His main research concerns Speech recognition, Artificial intelligence, Hidden Markov model, Pattern recognition and Natural language processing. His study looks at the relationship between Speech recognition and topics such as Word, which overlap with Vocabulary. The Artificial intelligence study combines topics in areas such as Pronunciation, Divergence and Computer vision.

Frank K. Soong studied Hidden Markov model and Mandarin Chinese that intersect with Phone and Syllable. His Pattern recognition research includes elements of Feature and Noise. His biological study spans a wide range of topics, including Context, Parametric statistics, Intelligibility, Sentence and Prosody.

He most often published in these fields:

  • Speech recognition (76.56%)
  • Artificial intelligence (57.14%)
  • Hidden Markov model (35.16%)

What were the highlights of his more recent work (between 2014-2021)?

  • Speech recognition (76.56%)
  • Artificial intelligence (57.14%)
  • Hidden Markov model (35.16%)

In recent papers he was focusing on the following fields of study:

His primary scientific interests are in Speech recognition, Artificial intelligence, Hidden Markov model, Speech synthesis and Artificial neural network. His biological study focuses on Speaker diarisation. His study in Artificial intelligence is interdisciplinary in nature, drawing from both Pronunciation, Pattern recognition, Separation and Natural language processing.

He has included themes like Visualization, Word, Reduction and Speech processing in his Hidden Markov model study. His Speech synthesis study combines topics in areas such as Linear prediction, Context, Filter and Time–frequency analysis. Frank K. Soong combines subjects such as Feature, Support vector machine and Language education with his study of Artificial neural network.

Between 2014 and 2021, his most popular works were:

  • Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers (88 citations)
  • Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis (81 citations)
  • Photo-real talking head with deep bidirectional LSTM (74 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Speech recognition
  • Statistics

Frank K. Soong mostly deals with Speech recognition, Artificial intelligence, Recurrent neural network, Hidden Markov model and Natural language processing. His work carried out in the field of Speech recognition brings together such families of science as Artificial neural network, Kullback–Leibler divergence and Representation. His studies in Artificial intelligence integrate themes in fields like Minification and Pattern recognition.

The study incorporates disciplines such as Precision and recall, Feature and Pronunciation in addition to Pattern recognition. His Hidden Markov model study incorporates themes from Face, Feature and Active appearance model. His work in Natural language processing tackles topics such as Word embedding which are related to areas like Named-entity recognition, Chunking, Feature engineering and Part-of-speech tagging.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

TTS Synthesis with Bidirectional LSTM based Recurrent Neural Networks

Yuchen Fan;Yao Qian;Feng-Long Xie;Frank K. Soong.
conference of the international speech communication association (2014)

498 Citations

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

Yusheng Li;Min Chu;Xin Zou;Frank Kao-Ping Soong.
(2007)

266 Citations

Automatic Speech and Speaker Recognition: Advanced Topics

Chin-Hui Lee;Frank K. Soong;Kuldip K. Paliwal.
(1999)

265 Citations

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

Yi Ning Chen;Min Chu;Jiali You;Frank Kao-Ping Soong.
(2006)

264 Citations

Handwriting-based user interface for correction of speech recognition errors

Lijuan Wang;Frank Kao-Ping Soong.
(2008)

237 Citations

Unnatural prosody detection in speech synthesis

Yong Zhao;Frank Kao-Ping Soong;Min Chu;Lijuan Wang.
(2007)

229 Citations

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

Yao Qian;Yuchen Fan;Wenping Hu;Frank K. Soong.
international conference on acoustics, speech, and signal processing (2014)

203 Citations

Automatic Speech and Speaker Recognition

Chin-Hui Lee;Frank K. Soong;Kuldip K. Paliwal.
(1996)

196 Citations

Cepstral channel normalization techniques for HMM-based speaker verification.

Aaron E. Rosenberg;Chin-Hui Lee;Frank K. Soong.
conference of the international speech communication association (1994)

172 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.
Speech Communication (2015)

160 Citations

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

Contact us

Best Scientists Citing Frank K. Soong

Junichi Yamagishi

Junichi Yamagishi

National Institute of Informatics

Publications: 89

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 61

Chin-Hui Lee

Chin-Hui Lee

Georgia Institute of Technology

Publications: 47

Simon King

Simon King

University of Edinburgh

Publications: 39

Keiichi Tokuda

Keiichi Tokuda

Nagoya Institute of Technology

Publications: 37

Helen Meng

Helen Meng

Chinese University of Hong Kong

Publications: 35

Zhen-Hua Ling

Zhen-Hua Ling

University of Science and Technology of China

Publications: 33

Hui Jiang

Hui Jiang

York University

Publications: 29

Jerome R. Bellegarda

Jerome R. Bellegarda

Apple (United States)

Publications: 28

Li Deng

Li Deng

Citadel

Publications: 27

Thomas R. Gruber

Thomas R. Gruber

Apple (United States)

Publications: 26

Heiga Zen

Heiga Zen

Google (United States)

Publications: 25

Lin-Shan Lee

Lin-Shan Lee

National Taiwan University

Publications: 24

Tomoki Toda

Tomoki Toda

Nagoya University

Publications: 23

Hirokazu Kameoka

Hirokazu Kameoka

NTT (Japan)

Publications: 19

Paavo Alku

Paavo Alku

Aalto University

Publications: 14

Something went wrong. Please try again later.