H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 34 Citations 6,619 304 World Ranking 6397 National Ranking 611

Overview

What is she best known for?

The fields of study she is best known for:

  • Artificial intelligence
  • Speech recognition
  • Machine learning

The scientist’s investigation covers issues in Artificial intelligence, Speech recognition, Natural language processing, Pronunciation and Speech processing. Her study ties her expertise on Pattern recognition together with the subject of Artificial intelligence. Her work investigates the relationship between Speech recognition and topics such as Phone that intersect with problems in Standard English.

Her Natural language processing research is multidisciplinary, incorporating perspectives in Document retrieval, Speech corpus, Word and Grammar. In her study, which falls under the umbrella issue of Pronunciation, Lexicon is strongly linked to Language transfer. Helen Meng combines subjects such as Annotation, The Internet, Data collection and Phrase with her study of Speech processing.

Her most cited work include:

  • A form-based dialogue manager for spoken language applications (289 citations)
  • Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings (241 citations)
  • Generating phonetic cognates to handle named entities in English-Chinese cross-language spoken document retrieval (212 citations)

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

Speech recognition, Artificial intelligence, Natural language processing, Speech synthesis and Hidden Markov model are her primary areas of study. While the research belongs to areas of Speech recognition, Helen Meng spends her time largely on the problem of Pronunciation, intersecting her research to questions surrounding Computer-aided. Her studies in Artificial intelligence integrate themes in fields like Machine learning and Pattern recognition.

Her Natural language processing research is multidisciplinary, relying on both Context, Word, Mandarin Chinese, Syllable and Dialog box. Helen Meng is studying Speech corpus, which is a component of Speech synthesis. Her research on Word error rate frequently connects to adjacent areas such as Reduction.

She most often published in these fields:

  • Speech recognition (62.33%)
  • Artificial intelligence (57.29%)
  • Natural language processing (42.71%)

What were the highlights of her more recent work (between 2017-2021)?

  • Speech recognition (62.33%)
  • Artificial intelligence (57.29%)
  • Artificial neural network (8.49%)

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

Her main research concerns Speech recognition, Artificial intelligence, Artificial neural network, Word error rate and Hidden Markov model. Her study in Speech recognition is interdisciplinary in nature, drawing from both Feature extraction, Discriminative model and Reduction. Her Artificial intelligence research is multidisciplinary, incorporating elements of Machine learning, Dialog box and Natural language processing.

Her biological study focuses on Sentence. Her research in Word error rate intersects with topics in Time delay neural network, Frame, Signal-to-noise ratio and Perplexity. Her Hidden Markov model study combines topics in areas such as Recurrent neural network, Conditional random field, Encoder, Speech corpus and Acoustic model.

Between 2017 and 2021, her most popular works were:

  • Semi-Supervised Graph Classification: A Hierarchical Graph Perspective (28 citations)
  • Speech Emotion Recognition Using Capsule Networks (26 citations)
  • Emotion Recognition from Variable-Length Speech Segments Using Deep Learning on Spectrograms. (26 citations)

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

  • Artificial intelligence
  • Speech recognition
  • Machine learning

Helen Meng mainly focuses on Speech recognition, Word error rate, Artificial neural network, Spectrogram and Discriminative model. The study incorporates disciplines such as Feature learning and Convolutional neural network in addition to Speech recognition. Her Word error rate study incorporates themes from Frame, Perplexity and Training set.

Her Discriminative model research incorporates themes from Time delay neural network, Modality, Audio-visual speech recognition and Speech coding. The Variable length study combines topics in areas such as Deep learning and Artificial intelligence. Her Artificial intelligence study frequently involves adjacent topics like Predictive modelling.

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

A form-based dialogue manager for spoken language applications

D. Goddeau;H. Meng;J. Polifroni;S. Seneff.
international conference on spoken language processing (1996)

442 Citations

Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings

Pengfei Liu;Shafiq Joty;Helen Meng.
empirical methods in natural language processing (2015)

339 Citations

WHEELS: a conversational system in the automobile classifieds domain

H. Meng;S. Busayapongchai;J. Giass;D. Goddeau.
international conference on spoken language processing (1996)

323 Citations

Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks

Lifa Sun;Shiyin Kang;Kun Li;Helen Meng.
international conference on acoustics, speech, and signal processing (2015)

249 Citations

Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trends

Zhen-Hua Ling;Shi-Yin Kang;Heiga Zen;Andrew Senior.
IEEE Signal Processing Magazine (2015)

231 Citations

Generating phonetic cognates to handle named entities in English-Chinese cross-language spoken document retrieval

H.M. Meng;Wai-Kit Lo;Berlin Chen;K. Tang.
ieee automatic speech recognition and understanding workshop (2001)

213 Citations

Phonetic posteriorgrams for many-to-one voice conversion without parallel data training

Lifa Sun;Kun Li;Hao Wang;Shiyin Kang.
international conference on multimedia and expo (2016)

208 Citations

From interface to content: translingual access and delivery of on-line information.

Victor W. Zue;Stephanie Seneff;James R. Glass;I. Lee Hetherington.
conference of the international speech communication association (1997)

190 Citations

Multi-distribution deep belief network for speech synthesis

Shiyin Kang;Xiaojun Qian;Helen Meng.
international conference on acoustics, speech, and signal processing (2013)

127 Citations

Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training.

Alissa M. Harrison;Wai-Kit Lo;Xiaojun Qian;Helen Meng.
symposium on languages, applications and technologies (2009)

113 Citations

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

Contact us

Best Scientists Citing Helen Meng

Haizhou Li

Haizhou Li

Chinese University of Hong Kong, Shenzhen

Publications: 73

Zhen-Hua Ling

Zhen-Hua Ling

University of Science and Technology of China

Publications: 37

Tomoki Toda

Tomoki Toda

Nagoya University

Publications: 36

Junichi Yamagishi

Junichi Yamagishi

National Institute of Informatics

Publications: 36

Thomas R. Gruber

Thomas R. Gruber

Apple (United States)

Publications: 32

Stephanie Seneff

Stephanie Seneff

MIT

Publications: 32

Hsin-Min Wang

Hsin-Min Wang

Academia Sinica

Publications: 27

Hirokazu Kameoka

Hirokazu Kameoka

NTT (Japan)

Publications: 27

Frank K. Soong

Frank K. Soong

Microsoft (United States)

Publications: 27

James Glass

James Glass

MIT

Publications: 25

Jerome R. Bellegarda

Jerome R. Bellegarda

Apple (United States)

Publications: 25

Lin-Shan Lee

Lin-Shan Lee

National Taiwan University

Publications: 24

Adam Cheyer

Adam Cheyer

Apple (United States)

Publications: 18

Alexandros Potamianos

Alexandros Potamianos

National Technical University of Athens

Publications: 18

Simon King

Simon King

University of Edinburgh

Publications: 17

Daniel Marcu

Daniel Marcu

University of Southern California

Publications: 16

Something went wrong. Please try again later.